nexus_similarity_search_api_estimate_corpus_entropy_profileFree
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 -- the real logic only exposes the mean marginal entropy across dimensions, not H(X_d) per individual dimension. Do NOT use expecting per-dimension granularity. Requires an x402 payment.
nexus_similarity_search_api_rank_items_by_nmi_cosine_fusionFree
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). Use this when you need semantically-calibrated similarity over a stateless corpus of up to 500k items without a vector database. Do NOT use for purely geometric nearest-neighbor search where NMI overhead is unnecessary, nor for corpora larger than 500k items per call. Requires an x402 payment.
nexus_similarity_search_api_score_pair_nmi_cosineFree
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. Unlike corpus-level ranking, alpha is NOT auto-calibrated for a single pair -- the real logic requires a fixed alpha (default 0.5); pass alpha explicitly for a specific blend. Do NOT use in a loop to score many pairs; batch them into rank_items_by_nmi_cosine_fusion instead. Requires an x402 payment.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

1 high

–Code scanremote-only server, no package to scann/a
Live reliabilityremote unreachable: Streamable HTTP error: Error POSTing to endpoint: {"status":"error","code":404,"message":"Application not found","request_id":"f0HQEZbKTvqUmStbnpoFkQ"}0/20
–Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
Auth qualityno auth information5/15
Maintenancelast push 59 days ago12/15
Maintainer identityregistry namespace matches repository owner7/10

Findings (1)

highRemote endpoint did not respondreliability.unreachable
Streamable HTTP error: Error POSTing to endpoint: {"status":"error","code":404,"message":"Application not found","request_id":"f0HQEZbKTvqUmStbnpoFkQ"}

Overall 40/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How Similarity Search API SDK compares

Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 40/100; higher than 6% of 3,470 Web search servers
Tools: 3; the typical Web search server has 5
Tools that change things: 0%; typical: 0%. Fewer write tools means less an agent can break
Uptime: 43%; of our recent checks; the typical remote Web search server answers 100%
Response time: 968 ms; faster than 10% of 2,238 Web search servers

What its tools let an agent do: 3 read

Install Similarity Search API SDK in Claude Code, Cursor or VS Code

claude mcp add --transport http similarity-search-api-sdk https://similarity-search-api-production.up.railway.app/mcp

Add to Cursor

What the publisher says

From the Similarity Search API SDK repository's README, as published. We do not edit it. Read it on GitHub

Similarity Search API

Stateless similarity search over pre-computed vectors — NMI (normalized mutual information) + cosine fusion, with an entropy-calibrated blending weight computed per request. No vector database, no index to maintain, no infrastructure to run.

Available both as a plain HTTP API and as an MCP server (5 tools) for AI agents.

Important: this operates on vectors, not raw text

This API does not embed text for you. query and corpus entries are pre-computed numeric vectors (e.g. from your own embedding model). If you need text-to-vector embedding first, run that upstream and pass the resulting vectors here.

Base URL

https://similarity-search-api-production.up.railway.app

Authentication

The 3 business endpoints (/similarity/search, /similarity/calibrate-alpha/v1, /similarity/batch-score) require no API key -- only a valid x402 payment (see "Pricing" below). The X-API-Key gate was dropped from these routes 2026-08-25; Stripe metered billing explicitly excludes them too, so passing a key does nothing on these 3 routes today. The deprecated, unpriced /similarity/calibrate-alpha (no /v1 suffix) still requires X-API-Key and always 501s regardless.

/health requires no authentication.

Pricing

Two ways to pay, same endpoints:

x402 (pay-per-call, USDC on Base) — currently on Base Sepolia testnet, $0.01/call, no account or API key required beyond the x402 payment flow itself. A request without payment gets 402 Payment Required with the payment details in the payment-required response header.
Stripe (metered billing) — for callers provisioned with an API key and a Stripe customer on the account.

Endpoints

POST /similarity/search

Rank a corpus against a query vector using the composite score.

{
  "query": { "id": "q1", "vector": [0.12, -0.4, 0.91, "..."] },
  "corpus": [
    { "id": "doc1", "vector": [0.10, -0.35, 0.88, "..."] },
    { "id": "doc2", "vector": [0.55, 0.02, -0.14, "..."] }
  ],
  "top_k": 10,
  "nmi_bins": 10,
  "alpha_override": null
}

All vectors in query and corpus must share the same dimensionality (2-4096 dims). topk up to 1000. alphaoverride (optional) pins the cosine/NMI blend weight instead of calibrating it from corpus entropy.

Response:

{
  "results": [
    { "id": "doc1", "composite_score": 0.91, "cosine_similarity": 0.89, "nmi_score": 0.94, "rank": 1 }
  ],
  "calibrated_alpha": 0.73,
  "corpus_entropy": 3.85,
  "query_id": "q1",
  "corpus_size": 2,
  "latency_ms": 43,
  "request_fingerprint": "..."
}

POST /similarity/calibrate-alpha/v1

Compute the entropy-calibrated alpha for a corpus without running a full search - useful for inspecting/debugging calibration behavior before committing to a search call.

POST /similarity/batch-score

Score up to 10,000 (vectora, vectorb) pairs with a fixed alpha - no corpus/entropy overhead.

{
  "pairs": [[[0.1, 0.2], [0.15, 0.19]]],
  "alpha": 0.5,
  "nmi_bins": 10
}

GET /health

Liveness probe. No auth required. Not billed (excluded from both Stripe and x402).

Note: POST /similarity/calibrate-alpha (without /v1) is a deprecated alias kept for backward compatibility - use /similarity/calibrate-alpha/v1.

MCP tools

Connect an MCP-compatible client (Claude, Cursor, etc.) to the streamable HTTP endpoint at: https://similarity-search-api-production.up.railway.app/mcp

Exposes 5 tools: rankitemsbynmicosinefusion, estimatecorpusentropyprofile, scorepairnmicosine, findoutliervectorsbynmideficit, calibratealphafromqueryentropy.

The scoring method

compositescore = alpha cosine(query, doc) + (1 - alpha) NMInormalized(query, doc)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

2026-10-31downgradeA → Dscore 40: Remote endpoint did not respond

Similarity Search API SDK: common questions

Is Similarity Search API SDK MCP server safe?: Not recommended: it is graded D (40/100). Read the Similarity Search API SDK safety report
How do I install Similarity Search API SDK?: It runs remotely at similarity-search-api-production.up.railway.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Similarity Search API SDK need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Similarity Search API SDK maintained?: The last commit was 64 days ago (2026-09-01). The latest release is v1.0.0.
Is Similarity Search API SDK up?: 43% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Similarity Search API SDK?: Servers from other publishers that do the same job: Everything Search MCP server.
How does Similarity Search API SDK compare with other Web search MCP servers?: safety score 40/100 (higher than 6% of 3,470 Web search servers); tools 3 (the typical Web search server has 5); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Similarity Search API SDK

Same job from other publishers: the closest match first, then the best rated.

Everything Search
Fast file search: Everything SDK on Windows, Spotlight (mdfind) on macOS, locate/plocate on Linux.
not reviewed
Established
A

Run it through the gateway

With the gateway added, ask your agent for it by name:

agent prompt

call io.github.nexus-mcp-infra/similarity-search-api-sdk → nexus_similarity_search_api_estimate_corpus_entropy_profile

Free per call. Metered, capped by your key, logged for reliability.

Add the gateway (gw.mcp.market)

Rating: —
Safety grade: D · 40/100
Stars: 0
Downloads/wk: –
Price: Free
Licence: —
Transport: Remote
Uptime: 43% · 12/28 checks
Version: 1.0.0
Category: Web search
Last release: 2026-09-01

Endpoint

https://similarity-search-api-production.up.railway.app/mcp

streamable-http

Own this server?

Claim it to keep the listing current and reply to reviews. Claiming never changes the grade or hides a review.

Claim listing

Badge for your README

Shows the safety grade and links back to this page. It updates itself after every scan and review.

[![mcp.market](https://mcp.market/badge/nexus-mcp-infra-similarity-search-api-sdk.svg)](https://mcp.market/server/nexus-mcp-infra-similarity-search-api-sdk)

How the badge works