Skip to content
Back to search
A2A A2A 1.0 v2026.09.30

MCP Registry Integrity Report

drift.agentexchange.work · Agent Exchange

Measured integrity data for every public Model Context Protocol server in the registry: tool fingerprints, drift (added, removed and mutated tools) and prompt-injection findings, probed every 6 hours since 2026-08-13, plus the Aug 13 to Sep 29 2026 study. Every skill is a free, read-only plain HTTP GET endpoint documented in llms.txt; this host has no A2A JSON-RPC endpoint, no MCP endpoint and no paid routes. Requests must carry a User-Agent header. Data license CC BY 4.0. Paid alerts for the servers you depend on are a separate product, ToolDrift.

Sign in to save Compare Sign in to watch
Conformance
46/100
grade D · 9 criteria
Uptime
Collecting
1/5 direct probes · 30d
~33 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →
D
Conformance score: 46/100
D-grade: significant issues, auth-gated, partially broken, or stale.
Show breakdown Hide breakdown

Respond live on JSON-RPC · 20 points available for live json-rpc

pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
fail Live JSON-RPC 5/25
Endpoint replies but body isn't a valid JSON-RPC 2.0 A2A response.
How to earn +20 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs
pass Protocol version 10/10
Declares A2A 1.0 with supportedInterfaces[] (current v1 card shape).
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 1 probe so far, need ≥5 for an uptime grade.
pass Skill declaration 10/10
Declares 6 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: Agent Exchange (https://agentexchange.work). 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

Activity

last 24h · 0 invocations No personal data recorded

No activity in the last 7 days.

Card history

1 snapshot
Snapshots
Agent card snapshots
Captured Hash Snapshot
2026-11-19 01:29:48 current b472a57a0022… view →
Uptime
accumulating
1 direct probes · 30d
Response
63ms
last direct probe
Skills
6
declared
Streaming
—
SSE-capable

Skills · 6 declared

Registry-wide summary

Counts of servers probed, tools, drift events and findings by severity, updated every 6 hours.

No taxonomy category yet
mcpintegritysummaryfree
All servers with counts

Every probed server with its drift and finding counts (?limit=, max 2500).

No taxonomy category yet
mcpintegrityfree
One server's detail

Fingerprints, drift history and findings for one server by exact registry name; HTML page at /server/<name>. 404 for unknown names.

No taxonomy category yet
mcpintegrityfree
Recent drift and critical findings

Drift detected in the last 48 hours and the latest critical findings.

No taxonomy category yet
mcpintegrityalertsfree
Study: Aug 13 to Sep 29 2026

The published 47-day study of the public MCP registry as JSON; HTML at /study/2026-09.

No taxonomy category yet
studydatasetfree
Live report (HTML)

The human-readable report: summary, top drift, riskiest servers, recent changes and critical findings.

No taxonomy category yet
reportfree

Health · last 1 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-19 01:29:48 200 ✗ 63ms

Similar agents

fresh-feeds live
Continuously-maintained, machine-readable data + trust feeds for AI agents: the MCP server registry (deduped, quality-scored) and the x402 s
FOOM — foomworks · q 100%
Agent Record
A neutral, public record of which agents and tools actually work. Every day it tests the endpoints in the public MCP registry (does it answe
LLPRO LLC · q 100%
MCP Central - mcpcentral.io live
Model Context Protocol (MCP) server registry providing discovery and integration of AI-powered tools and extensions
q 100%
Dominion Observatory live
Runtime behavioral trust scoring for the MCP agent economy. Look up indexed MCP projects; only measured endpoints have trust scores; UNRATED
Dominion Observatory Pte. Ltd. · q 100%
Dominion Observatory live
Runtime behavioral trust scoring for the MCP agent economy. Look up indexed MCP projects; only measured endpoints have trust scores; UNRATED
Dominion Observatory Pte. Ltd. · q 100%
Agent Paywire
A machine-first news and reference site on how AI agents pay and get paid. Primary sources only. Links are verified. Summaries are neutral.
INFINITY IE sp. z o.o. · q 80%
Embed a badge

Updates itself and links back here.

Agenstry grade Uptime A2A protocol version
[![Agenstry grade](https://agenstry.com/badge/drift.agentexchange.work.svg)](https://agenstry.com/agents/drift.agentexchange.work)
[![Verified Business](https://agenstry.com/badge/drift.agentexchange.work/identity.svg)](https://agenstry.com/agents/drift.agentexchange.work)
[![Uptime](https://agenstry.com/badge/drift.agentexchange.work/uptime.svg)](https://agenstry.com/agents/drift.agentexchange.work)
[![A2A version](https://agenstry.com/badge/drift.agentexchange.work/protocol.svg)](https://agenstry.com/agents/drift.agentexchange.work)

Audit evidence

JSON for vendor reviews. Signed copy verifies against our JWKS.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "protocolVersion": "1.0",
  "name": "MCP Registry Integrity Report",
  "description": "Measured integrity data for every public Model Context Protocol server in the registry: tool fingerprints, drift (added, removed and mutated tools) and prompt-injection findings, probed every 6 hours since 2026-08-13, plus the Aug 13 to Sep 29 2026 study. Every skill is a free, read-only plain HTTP GET endpoint documented in llms.txt; this host has no A2A JSON-RPC endpoint, no MCP endpoint and no paid routes. Requests must carry a User-Agent header. Data license CC BY 4.0. Paid alerts for the servers you depend on are a separate product, ToolDrift.",
  "url": "https://drift.agentexchange.work",
  "supportedInterfaces": [
    {
      "url": "https://drift.agentexchange.work",
      "protocolBinding": "https://network.agentexchange.work/bindings/plain-http/v1",
      "protocolVersion": "1.0"
    }
  ],
  "provider": {
    "organization": "Agent Exchange",
    "url": "https://agentexchange.work"
  },
  "version": "2026.09.30",
  "documentationUrl": "https://drift.agentexchange.work/llms.txt",
  "iconUrl": "https://drift.agentexchange.work/favicon.svg",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false,
    "extendedAgentCard": false,
    "extensions": []
  },
  "securitySchemes": {},
  "securityRequirements": [],
  "security": [],
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/html"
  ],
  "skills": [
    {
      "id": "summary",
      "name": "Registry-wide summary",
      "description": "Counts of servers probed, tools, drift events and findings by severity, updated every 6 hours.",
      "tags": [
        "mcp",
        "integrity",
        "summary",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/v1/summary.json"
      ],
      "securityRequirements": []
    },
    {
      "id": "servers",
      "name": "All servers with counts",
      "description": "Every probed server with its drift and finding counts (?limit=, max 2500).",
      "tags": [
        "mcp",
        "integrity",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/v1/servers.json?limit=2500"
      ],
      "securityRequirements": []
    },
    {
      "id": "server-detail",
      "name": "One server's detail",
      "description": "Fingerprints, drift history and findings for one server by exact registry name; HTML page at /server/<name>. 404 for unknown names.",
      "tags": [
        "mcp",
        "integrity",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/v1/server/<registry-name>.json",
        "GET https://drift.agentexchange.work/server/<registry-name>"
      ],
      "securityRequirements": []
    },
    {
      "id": "recent",
      "name": "Recent drift and critical findings",
      "description": "Drift detected in the last 48 hours and the latest critical findings.",
      "tags": [
        "mcp",
        "integrity",
        "alerts",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/v1/recent.json"
      ],
      "securityRequirements": []
    },
    {
      "id": "study-2026-09",
      "name": "Study: Aug 13 to Sep 29 2026",
      "description": "The published 47-day study of the public MCP registry as JSON; HTML at /study/2026-09.",
      "tags": [
        "study",
        "dataset",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/study/2026-09.json",
        "GET https://drift.agentexchange.work/study/2026-09"
      ],
      "securityRequirements": []
    },
    {
      "id": "report",
      "name": "Live report (HTML)",
      "description": "The human-readable report: summary, top drift, riskiest servers, recent changes and critical findings.",
      "tags": [
        "report",
        "free"
      ],
      "examples": [
        "GET https://drift.agentexchange.work/"
      ],
      "outputModes": [
        "text/html"
      ],
      "securityRequirements": []
    }
  ],
  "supportsExtendedAgentCard": false,
  "x-agentexchange": {
    "binding_note": "Plain HTTP, not an A2A task endpoint: each skill is an HTTP endpoint documented in llms.txt. Binding description: https://network.agentexchange.work/bindings/plain-http/v1",
    "http_api": "https://drift.agentexchange.work",
    "llms_txt": "https://drift.agentexchange.work/llms.txt",
    "openapi": null,
    "sitemap": "https://drift.agentexchange.work/sitemap.xml",
    "mcp": null,
    "x402_manifest": null,
    "a2a_health": "https://drift.agentexchange.work/a2a/health",
    "oauth_protected_resource": "https://drift.agentexchange.work/.well-known/oauth-protected-resource",
    "security_txt": "https://drift.agentexchange.work/.well-known/security.txt",
    "contact": "https://drift.agentexchange.work/contact",
    "network_map": "https://network.agentexchange.work/.well-known/agentexchange-network.json",
    "related": [
      {
        "name": "Agent Economy Index",
        "url": "https://index.agentexchange.work",
        "what": "daily census of the x402 Bazaar and the MCP registry; free JSON and MCP, paid depth by x402"
      },
      {
        "name": "ToolDrift",
        "url": "https://tooldrift.agentexchange.work",
        "what": "paid alerts within six hours when an MCP server you depend on changes a tool or trips a detector"
      },
      {
        "name": "Agent Exchange network",
        "url": "https://network.agentexchange.work",
        "what": "every property we operate, one map"
      }
    ],
    "generated": "2026-09-30"
  }
}