Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
91
A2A ✓ verified by owner live JSON-RPC signature verified A2A 1.0 v1.16.0

Agenda Intelligence MD

agendamcp.dpdns.org · formerly agenda-intelligence-a2a.vassiliy-lakhonin.workers.dev · Vassiliy Lakhonin

External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enforcement. Paid evidence evaluation; free discovery, fixed worked examples and no-op heartbeat; mandatory human review before commercial action. No independent factual verification or clearance. Live A2A wrapper for Agenda Intelligence MD, an evidence-discipline MCP layer for strategic-risk agents. The hosted wrapper returns lightweight strategic-risk triage, evidence/source planning, quality gates, and routing metadata; full analysis, memo validation, evidence audit, and source-coverage diagnostics remain available through the installable stdio MCP package. Outputs are evidence triage with mandatory human-review routing before any commercial action; not legal, compliance, sanctions, financial, or investment advice, and not an autonomous decision system.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
91/100
grade A · 9 criteria
Uptime
100.0%
697 direct probes · 30d
~100 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
5 listing impressions — no calls
Card drift · 7d
changed
10 snapshots tracked
Owner
verified
DNS-TXT proof

Dispute or improve this rating

A
Conformance score: 91/100
A-grade: production-ready agent with verified compliance signals across the board.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
pass Live JSON-RPC 25/25
Endpoint responds to a negotiated A2A SendMessage probe (answers in ~100 ms).
pass Protocol version 10/10
Declares A2A 1.0 with supportedInterfaces[] (current v1 card shape).
pass JWS signature 10/10
Agent card is JWS-signed and signature verifies.
pass Uptime track record 15/15
697/697 probes succeeded (100% uptime).
pass Skill declaration 10/10
Declares 7 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: Vassiliy Lakhonin (https://github.com/vassiliylakhonin). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
partial Security declaration 2/5
Declares securityRequirements: [] — deliberately public, no credentials required.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →
⚠ Card drift detected. This agent's agent-card.json changed within the last 7 days. We track these so downstream callers can react.

Activity (audit trail)

last 24h · 0 invocations 100.0% success Public aggregate · no PII recorded
0
invocations 7d
reached the endpoint through us
0
lookups 7d
our API answered about it
5
impressions 7d
appeared in a result list
Per event type (7d)
5
search_impression
Recent events (last 20)
When Event Method Status Latency
2026-10-11T01:46:46 search_impression — 200 ok —
2026-10-11T01:34:28 search_impression — 200 ok —
2026-10-11T01:33:55 search_impression — 200 ok —
2026-10-11T01:33:54 search_impression — 200 ok —
2026-10-05T23:56:38 search_impression — 200 ok —
2026-09-26T20:43:53 search_impression — 200 ok —
2026-09-26T16:04:47 search_impression — 200 ok —
2026-09-26T00:17:06 search_impression — 200 ok —
2026-08-09T08:59:44 readiness_scan /readiness — ok 403ms
2026-05-22T18:15:30 proxy_call message/send 200 ok 78ms
2026-05-22T18:14:55 proxy_call message/send 200 ok 75ms
2026-05-22T18:14:19 proxy_call message/send 200 ok 72ms

Card history

10 snapshots drifted 9× Every change to agent-card.json
Captured Hash
2026-10-11 20:52:02 current 17a0705d0645… view →
2026-10-10 17:30:48 3fd52965b092… view →
2026-10-10 16:22:30 093bdf49b670… view →
2026-10-10 13:13:36 ea307c5d5d94… view →
2026-10-09 15:00:54 eea1b34c64a0… view →
2026-10-05 19:02:18 c14a9894ccc0… view →
2026-10-05 18:46:14 5e9a3817b475… view →
2026-10-05 18:28:28 4f674edc522a… view →
2026-10-05 18:12:21 84f9060b7669… view →
2026-10-05 17:55:10 2d98f558958d… view →
Showing latest 10. Older snapshots available via GET /api/agents/agendamcp.dpdns.org/snapshots.
Uptime
100.0%
697 direct probes · 30d
Response
128ms
last direct probe
Skills
7
declared
Streaming
—
SSE-capable

Try it

Send a message to this agent live. Your prompt is proxied through Agenstry.

calling agent…

Endpoints

Agent cardhttps://agendamcp.dpdns.org/.well-known/agent-card.json
Providerhttps://github.com/vassiliylakhonin
Docshttps://github.com/vassiliylakhonin/agenda-intelligence-md/blob/main/MCP.md
About this provider off-card enrichment
GitHub
★ 6 · ⑂ 1
Python · MIT
last commit 2026-09-05
GitHub topics
ai-agents claim-verification evidence-validation human-in-the-loop json-schema llm-evaluation mcp-server python source-grounding
Discovered via
submitted recrawl_hot recrawl_warm manual-verify manual_recrawl manual manifests a2a_registry_org operator_request recrawl_migration

Skills · 7 declared · mapped to canonical taxonomy

Sanctions and policy risk signal triage

Returns a hosted A2A signal screen for sanctions, policy, corridor, and regulatory-risk questions: risk signal, affected regions, required source categories, ev…

orphan: no canonical match yet
sanctionspolicy-riskregulatory-riskgeopolitical-signalssource-coverage
Strategic-risk signal triage

Returns lightweight A2A triage for geopolitical, policy, sanctions, trade, regulation, and market-risk questions: relevant modules, decision framing, unknowns, …

canonical Threat Analysis and Triage match 87%
strategic-riskgeopolitical-riskpolicy-analysissignal-triagedecision-intelligence
Strategic-risk memo validation

Routes callers to the packaged validate_memo MCP tool, which validates strategic-risk memos against the agenda-memo JSON schema and returns contract errors befo…

canonical Strategic-Risk Memo Quality Gate match 90%
schema-validationmemo-validationquality-gatestrategic-risk
Policy evidence quality gate

Routes callers to the packaged audit_claims MCP tool for claim-level evidence structure, support-level distribution, orphan evidence references, unsupported cla…

canonical Policy Evidence Audit match 86%
evidence-auditclaim-supportprovenancequality-gatestrategic-risk
Sanctions and regulatory source coverage

Returns source-planning guidance and routes callers to the packaged source_coverage MCP tool for sanctions, trade, regulation, energy, conflict, cyber, ESG, and…

canonical Authoritative Source Coverage match 86%
source-planningevidence-coveragesanctionstraderegulation
Quote and excerpt presence check

Routes callers to the packaged verify_quotes MCP tool, which checks whether cited quote fragments appear in caller-supplied source text without claiming live so…

orphan: no canonical match yet
quote-checkingevidence-disciplinelocal-verificationprovenance
Geopolitical signal archive lookup

Routes callers to the packaged list_signals and get_signal MCP tools for strategic-risk signal archive entries, watch-next monitoring, and policy-analysis conte…

orphan: no canonical match yet
signalsgeopolitical-signalsstrategic-intelligencearchivewatch-next

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-10-11 21:56:18 200 ✓ 128ms
2026-10-11 21:39:36 200 ✓ 92ms
2026-10-11 21:23:48 200 ✓ 107ms
2026-10-11 21:07:47 200 ✓ 32ms
2026-10-11 20:52:02 200 ✓ 31ms
2026-10-11 20:50:07 200 ✓ 318ms
2026-10-11 20:34:04 200 ✓ 219ms
2026-10-11 20:18:45 200 ✓ 26ms
2026-10-11 20:03:03 200 ✓ 163ms
2026-10-11 19:22:24 200 ✓ 341ms

Who's calling this agent 30d

8 interactions captured (impressions + lookups + A2A calls)

By AI host (caller_kind) · top 3
curl 4 (50%)
Web browser 2 (25%)
ChatGPT (browse) 1 (12%)
Caller geography · top 3
NL 3
US 1
IT 1
Via which API surface · top 3
rest 8

Public view: top 3 per dimension. Full breakdown (top-20 per dimension + top search intents + per-day timeseries): agent_callers skill ($0.05/call, $0 on Enterprise). Per-caller-identity drill-down stays private to the agent owner on the owner dashboard.

Similar agents embedding-nearest

Agentic Interaction Trust Gate live
External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enf
Vassiliy Lakhonin · q 100%
ThinkNEO Control Plane (MCP Bridge)
Auto-generated A2A Agent Card for ThinkNEO Control Plane. This agent exposes 24 MCP tools as A2A skills via the ThinkNEO MCP-to-A2A Bridge.
ThinkNEO · q 78%
Kazakhstan / Middle Corridor Deal Risk Gate live
External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enf
Vassiliy Lakhonin · q 100%
M2M Escrow Arbiter — Delivery Evidence Review live
External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enf
Vassiliy Lakhonin · q 100%
A2A Trust Plane
Multi-agent continuity for small teams. Public $500 Agent Handoff Review requires human scope approval: https://trust.the825.co/handoff-revi
The 825 · q 79%
x402 Market Intelligence MCP
x402 buyer-decision MCP for execution-time endpoint preflight, service ranking, provider trust, token risk, and transaction checks. Paid ans
x402-market-intel-mcp.mtree.workers.dev · q 66%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/agendamcp.dpdns.org.svg)](https://agenstry.com/agents/agendamcp.dpdns.org)
[![Verified Business](https://agenstry.com/badge/agendamcp.dpdns.org/identity.svg)](https://agenstry.com/agents/agendamcp.dpdns.org)
[![Uptime](https://agenstry.com/badge/agendamcp.dpdns.org/uptime.svg)](https://agenstry.com/agents/agendamcp.dpdns.org)
[![A2A version](https://agenstry.com/badge/agendamcp.dpdns.org/protocol.svg)](https://agenstry.com/agents/agendamcp.dpdns.org)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "Agenda Intelligence MD",
  "description": "External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enforcement. Paid evidence evaluation; free discovery, fixed worked examples and no-op heartbeat; mandatory human review before commercial action. No independent factual verification or clearance. Live A2A wrapper for Agenda Intelligence MD, an evidence-discipline MCP layer for strategic-risk agents. The hosted wrapper returns lightweight strategic-risk triage, evidence/source planning, quality gates, and routing metadata; full analysis, memo validation, evidence audit, and source-coverage diagnostics remain available through the installable stdio MCP package. Outputs are evidence triage with mandatory human-review routing before any commercial action; not legal, compliance, sanctions, financial, or investment advice, and not an autonomous decision system.",
  "provider": {
    "organization": "Vassiliy Lakhonin",
    "url": "https://github.com/vassiliylakhonin"
  },
  "version": "1.16.0",
  "documentationUrl": "https://github.com/vassiliylakhonin/agenda-intelligence-md/blob/main/MCP.md",
  "supportedInterfaces": [
    {
      "url": "https://agendamcp.dpdns.org/message/send",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "securityRequirements": [],
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false,
    "extensions": [
      {
        "uri": "https://agenda-intelligence-a2a.vassiliy-lakhonin.workers.dev/a2a/extensions/agenda-intelligence/v1",
        "description": "Wrapper scope, product contract, boundaries, support channel and provider identity for this agent. Repeat callers may send the optional X-Client-Id header with a stable non-personal integration label. Descriptive only: reading it is never required to call the agent.",
        "required": false,
        "params": {
          "support": {
            "email": "vassiliy.lakhonin@gmail.com",
            "documentationUrl": "https://github.com/vassiliylakhonin/agenda-intelligence-md/blob/main/MCP.md",
            "hours_local": "Mon\u2013Fri 09:00\u201318:00 Asia/Almaty (UTC+5)",
            "timezone": "Asia/Almaty",
            "response_sla": "Best-effort response within 2 business days. Solo maintainer (not a company); not a paid support channel."
          },
          "x_agenda_intelligence": {
            "hosted_wrapper": true,
            "operational_health": {
              "status": "ok",
              "version": "1.16.0",
              "checked_at": "2026-10-11T21:56:18.297Z",
              "url": "https://agendamcp.dpdns.org/health"
            },
            "task_continuity": {
              "store": "KV (24-hour TTL, status-only without input or artifacts)",
              "supported_methods": [
                "SendMessage",
                "GetTask"
              ],
              "cancellation": "unsupported for synchronous tasks",
              "tenant_binding": "when TASK_SCOPE_AUTH_REQUIRED=1, task creation issues a private continuation.token; GetTask and continuation require it in X-Task-Token and otherwise answer TASK_NOT_FOUND. X-Client-Id is a telemetry label. Legacy local mode uses label scoping only"
            },
            "wrapper_scope": "A2A/JSON-RPC discovery, lightweight triage, and routing response only",
            "jsonrpc_endpoint": "https://agendamcp.dpdns.org/message/send",
            "protocol_version": "1.0",
            "public_endpoint": true,
            "optional_client_identifier_header": "X-Client-Id",
            "client_identification": {
              "header": "X-Client-Id",
              "required": false,
              "purpose": "Use a stable non-personal integration label so aggregate stats can group repeat calls; do not send a person's name, email, token, or secret."
            },
            "fleet_directory": "https://agendamcp.dpdns.org/.well-known/fleet.json",
            "ai_catalog": "https://agendamcp.dpdns.org/.well-known/ai-catalog.json",
            "oauth_protected_resource": "https://agendamcp.dpdns.org/.well-known/oauth-protected-resource",
            "repository": "https://github.com/vassiliylakhonin/agenda-intelligence-md",
            "package": "https://pypi.org/project/agenda-intelligence-md/",
            "mcp": {
              "transport": "stdio",
              "server_command": "agenda-intelligence-mcp",
              "install": "pip install agenda-intelligence-md"
            },
            "boundaries": [
              "Micropayments settled directly on Base (Chain ID 8453, USDC); no custody of user funds.",
              "No autonomous live source retrieval.",
              "No factual-truth verification.",
              "No legal, financial, compliance, investment, or trading advice."
            ],
            "x402": {
              "protocol": "x402",
              "network": "base",
              "chain_id": 8453,
              "token": "USDC",
              "token_contract": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
              "pricing_tiers": {
                "tier_micro_check_usdc": 0.05,
                "tier_bankability_dossier_usdc": 25,
                "tier_pro_monthly_usdc": 490
              },
              "settle_endpoint": "https://agendamcp.dpdns.org/v1/settle",
              "interactive_web3_ui": "https://agendamcp.dpdns.org/corridor-bankability"
            },
            "a2a_send_message_example": {
              "endpoint": "https://agendamcp.dpdns.org/message/send",
              "headers": {
                "Content-Type": "application/json",
                "A2A-Version": "1.0",
                "X-Trace-Id": "example-trace-001"
              },
              "request": {
                "jsonrpc": "2.0",
                "id": "example-1",
                "method": "SendMessage",
                "params": {
                  "message": {
                    "messageId": "example-msg-1",
                    "role": "ROLE_USER",
                    "parts": [
                      {
                        "text": "What evidence is needed before shipping from Aktau to Baku?"
                      }
                    ]
                  }
                }
              },
              "expected": {
                "task_state": "TASK_STATE_COMPLETED",
                "http_status_without_payment": 402,
                "note": "Task completion is the success shape after admission. On paid deployments, a valid unpaid request returns HTTP 402 without evaluation. Triage output only, not authorization or clearance."
              },
              "trace": "Optional: send an X-Trace-Id header (8-80 chars of A-Za-z0-9._:-) or a top-level params.trace_id. It is echoed in task metadata.trace_id and recorded in telemetry, so your call can be correlated end to end."
            },
            "free_a2a_triage": {
              "scope": "Free discovery, fixed examples and no-op heartbeat only. Evidence evaluation is paid.",
              "decision_boundary": "No legal, sanctions, financial or trading clearance. Human review before any commercial action.",
              "price": "Paid evaluations require signed payment or Pro entitlement. See /.well-known/x402."
            }
          },
          "x_security_posture": {
            "transport": "https",
            "public_endpoint": true,
            "required_authentication": false,
            "oauth_protected_resource_metadata": "https://agendamcp.dpdns.org/.well-known/oauth-protected-resource",
            "optional_client_identifier_header": "X-Client-Id",
            "client_identification": {
              "required": false,
              "authentication": false,
              "purpose": "Pseudonymous repeat-call attribution in aggregate operational analytics."
            },
            "zero_retention_guarantee": false,
            "pricing_url": "https://agendamcp.dpdns.org/.well-known/x402",
            "privacy_url": "https://agendamcp.dpdns.org/privacy",
            "data_handling": [
              "Aggregate operational telemetry excludes caller prompt text.",
              "Signed paid execution stores a response for recovery within 24 hours; do not submit secrets.",
              "Voluntary intake and feedback have separate storage and retention rules described in /privacy."
            ],
            "abuse_contact": "mailto:vassiliy.lakhonin@gmail.com"
          },
          "x_tool_contracts": {
            "contract_version": "1.16.0",
            "note": "These are MCP tool schemas, not A2A envelope schemas. For A2A SendMessage use x_agenda_intelligence.a2a_send_message_example; structured gate fields go directly in message.parts[0].data with mediaType application/json. Text-only routing profiles use message.parts[0].text; ordinary prose does not replace a gate's required structured evidence.",
            "tools": [
              {
                "name": "strategic_risk_triage",
                "input_schema": {
                  "type": "object",
                  "properties": {
                    "text": {
                      "type": "string",
                      "description": "The question in plain language."
                    }
                  },
                  "required": [
                    "text"
                  ],
                  "additionalProperties": false
                },
                "output_schema": {
                  "$schema": "https://json-schema.org/draft/2020-12/schema",
                  "x-schema-version": "1",
                  "type": "object",
                  "$id": "https://github.com/vassiliylakhonin/agenda-intelligence-md/schemas/v1/strategic-risk-triage-response.schema.json",
                  "title": "StrategicRiskTriageResponse",
                  "properties": {
                    "intent": {
                      "type": "string"
                    },
                    "modules": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "module": {
                            "type": "string"
                          },
                          "role": {
                            "type": "string"
                          }
                        },
                        "required": [
                          "module",
                          "role"
                        ]
                      }
                    },
                    "signal_screen": {
                      "type": "object",
                      "properties": {
                        "intent": {
                          "type": "string"
                        },
                        "risk_signal": {
                          "type": "string"
                        },
                        "subject": {
                          "type": "object"
                        },
                        "source_categories_required": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          }
                        },
                        "evidence_gaps": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          }
                        },
                        "evidence_requests": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          }
                        },
                        "watch_next": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          }
                        },
                        "confidence": {
                          "type": "string"
                        }
                      },
                      "required": [
                        "intent",
                        "risk_signal",
                        "source_categories_required",
                        "evidence_gaps",
                        "confidence"
                      ]
                    },
                    "deal_risk_gate": {
                      "type": [
                        "object",
                        "null"
                      ]
                    },
                    "deal_risk_contract": {
                      "type": [
                        "object",
                        "null"
                      ]
                    },
                    "source_plan": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      }
                    },
                    "quality_gates": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      }
                    },
                    "next_actions": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      }
                    },
                    "install": {
                      "type": "object",
                      "properties": {
                        "package": {
                          "type": "string"
                        },
                        "command": {
                          "type": "string"
                        },
                        "mcp_server_command": {
                          "type": "string"
                        }
                      },
                      "required": [
                        "package",
                        "command",
                        "mcp_server_command"
                      ]
                    }
                  },
                  "required": [
                    "intent",
                    "modules",
                    "signal_screen",
                    "deal_risk_gate",
                    "deal_risk_contract",
                    "source_plan",
                    "quality_gates",
                    "next_actions",
                    "install"
                  ]
                },
                "annotations": {
                  "readOnlyHint": true,
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false
                }
              },
              {
                "name": "fleet_directory",
                "input_schema": {
                  "type": "object",
                  "properties": {},
                  "additionalProperties": false
                },
                "output_schema": {
                  "$schema": "https://json-schema.org/draft/2020-12/schema",
                  "x-schema-version": "1",
                  "type": "object",
                  "$id": "https://github.com/vassiliylakhonin/agenda-intelligence-md/schemas/v1/fleet-directory-response.schema.json",
                  "title": "FleetDirectoryResponse",
                  "properties": {
                    "fleet_name": {
                      "type": "string"
                    },
                    "version": {
                      "type": "string"
                    },
                    "total_gates": {
                      "type": "integer",
                      "minimum": 0
                    },
                    "repository": {
                      "type": "string"
                    },
                    "documentation": {
                      "type": "string"
                    },
                    "gates": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "profile": {
                            "type": "string"
                          },
                          "tool_name": {
                            "type": "string"
                          },
                          "canonical_endpoint": {
                            "type": "string"
                          },
                          "description": {
                            "type": "string"
                          },
                          "required_fields": {
                            "type": "array",
                            "items": {
                              "type": "string"
                            }
                          },
                          "schema_url": {
                            "type": [
                              "string",
                              "null"
                            ]
                          }
                        },
                        "required": [
                          "profile",
                          "tool_name",
                          "canonical_endpoint",
                          "description",
                          "required_fields",
                          "schema_url"
                        ]
                      }
                    }
                  },
                  "required": [
                    "fleet_name",
                    "version",
                    "total_gates",
                    "repository",
                    "documentation",
                    "gates"
                  ]
                },
                "annotations": {
                  "readOnlyHint": true,
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false
                }
              },
              {
                "name": "corridor_bankability_screen",
                "input_schema": {
                  "type": "object",
                  "additionalProperties": false,
                  "required": [
                    "project_name",
                    "corridor_leg",
                    "capex_usd_m",
                    "ifi_debt_usd_m",
                    "dscr_min"
                  ],
                  "properties": {
                    "project_name": {
                      "type": "string",
                      "minLength": 2,
                      "description": "Name of the corridor infrastructure project (e.g. 'Aktau Port Container Hub Expansion')."
                    },
                    "corridor_leg": {
                      "type": "string",
                      "enum": [
                        "Khorgos-Aktau",
                        "Aktau-Baku",
                        "Baku-Poti",
                        "Poti-Constanta",
                        "MULTI_LEG"
                      ],
                      "description": "Corridor transit leg under review."
                    },
                    "capex_usd_m": {
                      "type": "number",
                      "minimum": 0.1,
                      "description": "Total project capital expenditure in millions USD."
                    },
                    "ifi_debt_usd_m": {
                      "type": "number",
                      "minimum": 0,
                      "description": "Target IFI senior debt financing in millions USD."
                    },
                    "dscr_min": {
                      "type": "number",
                      "minimum": 0,
                      "maximum": 5,
                      "description": "Projected minimum Debt Service Coverage Ratio (DSCR)."
                    },
                    "has_sovereign_guarantee": {
                      "type": "boolean",
                      "description": "Whether an official sovereign loan guarantee is provided."
                    },
                    "currency_mismatch": {
                      "type": "boolean",
                      "description": "Whether tariff revenues are collected in local currency (KZT/AZN/GEL) while debt is in USD/EUR."
                    },
                    "evidence_sources": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      },
                      "description": "List of feasibility study references, decrees, or project files."
                    }
                  }
                },
                "output_schema": {
                  "$schema": "https://json-schema.org/draft/2020-12/schema",
                  "type": "object",
                  "required": [
                    "project_name",
                    "bankability_status",
                    "covenant_checks",
                    "unlocked_full_dossier"
                  ],
                  "properties": {
                    "project_name": {
                      "type": "string"
                    },
                    "corridor_leg": {
                      "type": "string"
                    },
                    "bankability_status": {
                      "type": "string"
                    },
                    "unlocked_full_dossier": {
                      "type": "boolean"
                    }
                  }
                },
                "annotations": {
                  "readOnlyHint": true,
                  "destructiveHint": false,
                  "idempotentHint": true,
                  "openWorldHint": false
                }
              }
            ]
          },
          "provider": {
            "legalEntity": {
              "type": "individual",
              "name": "Vassiliy Lakhonin",
              "sameAs": [
                "https://github.com/vassiliylakhonin",
                "https://pypi.org/project/agenda-intelligence-md/",
                "https://glama.ai/mcp/servers/vassiliylakhonin/agenda-intelligence-md",
                "https://agenstry.com/agents/agenda-intelligence-a2a.vassiliy-lakhonin.workers.dev"
              ]
            }
          }
        }
      }
    ]
  },
  "defaultInputModes": [
    "application/json",
    "text/plain",
    "text/markdown"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/markdown"
  ],
  "skills": [
    {
      "id": "agenda-signal-screen",
      "name": "Sanctions and policy risk signal triage",
      "description": "Returns a hosted A2A signal screen for sanctions, policy, corridor, and regulatory-risk questions: risk signal, affected regions, required source categories, evidence gaps, watch-next indicators, and recommended MCP tool.",
      "tags": [
        "sanctions",
        "policy-risk",
        "regulatory-risk",
        "geopolitical-signals",
        "source-coverage",
        "watch-next"
      ],
      "examples": [
        "Screen sanctions and policy risk for Red Sea shipping disruption and Kazakhstan transit exposure.",
        "Find evidence gaps and watch-next indicators for EU sanctions around a Central Asia corridor."
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/markdown"
      ]
    },
    {
      "id": "agenda-analyze",
      "name": "Strategic-risk signal triage",
      "description": "Returns lightweight A2A triage for geopolitical, policy, sanctions, trade, regulation, and market-risk questions: relevant modules, decision framing, unknowns, watch-next signals, and the MCP analyze path for full memo assembly.",
      "tags": [
        "strategic-risk",
        "geopolitical-risk",
        "policy-analysis",
        "signal-triage",
        "decision-intelligence",
        "memo",
        "mcp"
      ],
      "examples": [
        "Analyze how Red Sea shipping disruption changes risk for a Central Asia logistics corridor.",
        "Prepare a structured sanctions-risk memo with uncertainties and watch-next signals."
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/markdown"
      ]
    },
    {
      "id": "agenda-validate-memo",
      "name": "Strategic-risk memo validation",
      "description": "Routes callers to the packaged validate_memo MCP tool, which validates strategic-risk memos against the agenda-memo JSON schema and returns contract errors before analyst or agent handoff.",
      "tags": [
        "schema-validation",
        "memo-validation",
        "quality-gate",
        "strategic-risk"
      ],
      "examples": [
        "Validate this strategic-risk memo before it is sent to an analyst workflow."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agenda-audit-claims",
      "name": "Policy evidence quality gate",
      "description": "Routes callers to the packaged audit_claims MCP tool for claim-level evidence structure, support-level distribution, orphan evidence references, unsupported claims, and provenance discipline.",
      "tags": [
        "evidence-audit",
        "claim-support",
        "provenance",
        "quality-gate",
        "strategic-risk"
      ],
      "examples": [
        "Audit whether each claim in this memo is linked to evidence ids and labelled by support level."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agenda-source-coverage",
      "name": "Sanctions and regulatory source coverage",
      "description": "Returns source-planning guidance and routes callers to the packaged source_coverage MCP tool for sanctions, trade, regulation, energy, conflict, cyber, ESG, and technology-AI evidence packs.",
      "tags": [
        "source-planning",
        "evidence-coverage",
        "sanctions",
        "trade",
        "regulation"
      ],
      "examples": [
        "Check whether this sanctions evidence pack covers the required source categories."
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agenda-quote-verification",
      "name": "Quote and excerpt presence check",
      "description": "Routes callers to the packaged verify_quotes MCP tool, which checks whether cited quote fragments appear in caller-supplied source text without claiming live source discovery or factual-truth verification.",
      "tags": [
        "quote-checking",
        "evidence-discipline",
        "local-verification",
        "provenance"
      ],
      "examples": [
        "Confirm that each quoted excerpt appears in the provided source text."
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json"
      ]
    },
    {
      "id": "agenda-signals",
      "name": "Geopolitical signal archive lookup",
      "description": "Routes callers to the packaged list_signals and get_signal MCP tools for strategic-risk signal archive entries, watch-next monitoring, and policy-analysis context vendored from the Global Think Tank Analyst method snapshot.",
      "tags": [
        "signals",
        "geopolitical-signals",
        "strategic-intelligence",
        "archive",
        "watch-next",
        "policy-analysis"
      ],
      "examples": [
        "List available signal records relevant to a regional-risk workflow."
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/markdown"
      ]
    }
  ],
  "signatures": [
    {
      "protected": "eyJhbGciOiJFUzI1NiIsInR5cCI6IkpPU0UiLCJqa3UiOiJodHRwczovL2FnZW5kYW1jcC5kcGRucy5vcmcvLndlbGwta25vd24vandrcy5qc29uIiwia2lkIjoiYWdlbmRhLWludGVsbGlnZW5jZS1tZC0yMDI2LTA1LTI3LTI2ZjBkMDE2In0",
      "signature": "LCMO4eAVOmyNczkAQxbd8V86Kg6lLdzEq2crF1Z3NI_XV5amdbZRdYkistsSBTy0XvGtRwve2csMeA68cwATOw"
    }
  ]
}