Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
76
A2A v1.0.0 x402 micropay

Calibrated Similarity Search API

similarity-search-api-production.up.railway.app · nexus-mcp-infra

Stateless NMI + cosine fusion with entropy-driven alpha calibration

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain similarity-search-api-production.up.railway.app via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership
🔔 Watch this agent. Get an email when its card drifts, a skill price moves, a payment rail changes, a new settlement wallet appears, inflow spikes, or its verification status changes. 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
47/100
grade D · 9 criteria
Uptime
97.5%
40 direct probes · 30d
~470 ms response
Observed inflow · 30d
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 47/100
D-grade: significant issues, auth-gated, partially broken, or stale.
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).
fail Live JSON-RPC 0/25
Card declares a URL but that URL returns 404.
How to earn +25 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.
Docs →
fail Protocol version 0/10
No protocolVersion in card.
How to earn +10 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
pass Uptime track record 15/15
39/40 probes succeeded (98% uptime).
pass Skill declaration 10/10
Declares 3 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: nexus-mcp-infra (https://github.com/nexus-mcp-infra/similarity-search-api-sdk). 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 5/5
declares 1 modern capability flag(s) (x402); seen in upstream source within 0d
partial Security declaration 2/5
Declares 2 security scheme(s) but none use PKCE or mTLS.
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 (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Captured Hash
2026-07-27 10:52:24 current 4b65ca0c9f57… view →
Uptime
97.5%
40 direct probes · 30d
Response
707ms
last direct probe
Skills
3
declared
Streaming
SSE-capable

Skills · 3 declared · mapped to canonical taxonomy

NMI-Cosine Fused Similarity Ranking

Ranks a corpus of items against a query vector using a calibrated fusion score (alpha * cosine + (1-alpha) * NMI_normalizado), where alpha is auto-derived from …

canonical Vector Search and Embeddings match 82%
similarity-searchembeddingsnmicosine-similarity
Corpus Entropy and Calibrated Alpha Estimator

Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_c…

canonical Model Evaluation and Benchmarking match 82%
entropycalibration
Single-Pair NMI-Cosine Scorer

Computes the NMI-cosine fusion score for exactly one (query, target) vector pair at a fixed alpha. Use for explainability, debugging, or unit-level validation o…

canonical Model Evaluation and Benchmarking match 80%
similarity-searchdebugging

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-08-19 10:47:32 200 707ms
2026-08-19 02:16:39 200 377ms
2026-08-18 17:45:13 200 427ms
2026-08-18 06:48:32 200 393ms
2026-08-17 23:08:52 200 370ms
2026-08-17 05:26:51 200 383ms
2026-08-16 18:29:21 200 398ms
2026-08-16 06:44:36 200 384ms
2026-08-16 02:55:14 200 405ms
2026-08-15 07:05:35 200 717ms

Cheaper or better alternatives per-skill

↑ 2 higher quality

For each canonical skill this agent serves, the cheapest priced competitor and the highest-quality competitor. Only shown when at least one beats the current agent. Skills where this agent is already best on both axes are hidden.

Similar agents embedding-nearest

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%
assay.nominal-labs.com
Quality score for any x402 service, earned by real paid probes with on-chain receipts: composite 0-100, component breakdown (payment settlem
assay.nominal-labs.com · q 65%
AIScan live
AI visibility auditing for websites. 4 scores (AEO, GEO, Agent Readiness, MCP Readiness - the only scanner that checks MCP) plus Brand Visib
AIScan · q 100%
JarvisClaw
AI API routing platform — 40+ models, marketplace services, pay per call via x402 USDC micropayments. No account needed.
JarvisClaw · q 80%
Amalgix
Cross-model evidence pipeline for AI agents. Specialized extraction and verification models deliver source-grounded facts from financial fil
Amalgix · q 75%
Macaroon Network live
Marketplace for agent-purchasable capabilities. Every listing carries a falsifiable acceptance predicate; payment settles only when the pred
api.macaroonnetwork.com · q 100%

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
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/similarity-search-api-production.up.railway.app.svg)](https://agenstry.com/agents/similarity-search-api-production.up.railway.app)
[![Verified Business](https://agenstry.com/badge/similarity-search-api-production.up.railway.app/identity.svg)](https://agenstry.com/agents/similarity-search-api-production.up.railway.app)
[![Uptime](https://agenstry.com/badge/similarity-search-api-production.up.railway.app/uptime.svg)](https://agenstry.com/agents/similarity-search-api-production.up.railway.app)
[![A2A version](https://agenstry.com/badge/similarity-search-api-production.up.railway.app/protocol.svg)](https://agenstry.com/agents/similarity-search-api-production.up.railway.app)

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": "Calibrated Similarity Search API",
  "description": "Stateless NMI + cosine fusion with entropy-driven alpha calibration",
  "url": "https://similarity-search-api-production.up.railway.app",
  "version": "1.0.0",
  "documentationUrl": "https://similarity-search-api-production.up.railway.app/docs",
  "provider": {
    "organization": "nexus-mcp-infra",
    "url": "https://github.com/nexus-mcp-infra/similarity-search-api-sdk"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "stateTransitionHistory": false
  },
  "defaultInputModes": [
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json"
  ],
  "additionalInterfaces": [
    {
      "url": "https://similarity-search-api-production.up.railway.app/mcp",
      "transport": "MCP"
    }
  ],
  "securitySchemes": {
    "apiKeyHeader": {
      "type": "apiKey",
      "in": "header",
      "name": "X-API-Key"
    },
    "x402Payment": {
      "type": "apiKey",
      "in": "header",
      "name": "X-PAYMENT",
      "description": "x402 payment proof (USDC, Base Sepolia testnet) required on paid operations -- not a classic auth scheme."
    }
  },
  "security": [
    {
      "apiKeyHeader": [],
      "x402Payment": []
    }
  ],
  "skills": [
    {
      "id": "nexus_similarity_search_api_rank_items_by_nmi_cosine_fusion",
      "name": "NMI-Cosine Fused Similarity Ranking",
      "description": "Ranks a corpus of items against a query vector using a calibrated fusion score (alpha * cosine + (1-alpha) * NMI_normalizado), where alpha is auto-derived from the corpus's marginal entropy unless overridden. Results are identified by their 0-indexed position in corpus_vectors (this tool does not accept explicit item IDs). Requires a valid api_key (same as X-API-Key) and an x402 payment.",
      "tags": [
        "similarity-search",
        "embeddings",
        "nmi",
        "cosine-similarity"
      ]
    },
    {
      "id": "nexus_similarity_search_api_estimate_corpus_entropy_profile",
      "name": "Corpus Entropy and Calibrated Alpha Estimator",
      "description": "Computes the aggregate entropy-calibrated alpha for a corpus without running a full search -- useful to inspect before committing to a large rank_items_by_nmi_cosine_fusion call. Returns a single aggregate corpus_entropy value, not a per-dimension breakdown. Requires a valid api_key (same as X-API-Key) and an x402 payment.",
      "tags": [
        "entropy",
        "calibration"
      ]
    },
    {
      "id": "nexus_similarity_search_api_score_pair_nmi_cosine",
      "name": "Single-Pair NMI-Cosine Scorer",
      "description": "Computes the NMI-cosine fusion score for exactly one (query, target) vector pair at a fixed alpha. Use for explainability, debugging, or unit-level validation of fusion scores before running full corpus ranking. Requires a valid api_key (same as X-API-Key) and an x402 payment.",
      "tags": [
        "similarity-search",
        "debugging"
      ]
    }
  ],
  "metadata": {
    "protocol_note": "This service implements the Model Context Protocol (MCP) at /mcp, not A2A's own JSONRPC/gRPC/HTTP+JSON task methods (message/send, tasks/get, etc.). This Agent Card is provided for discovery/indexing purposes; A2A-conformant task orchestration is not implemented."
  }
}