# dev.reqistry/mcp

Discover, compare, and monitor 1,400+ APIs directly from your AI coding agent.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 2.0.0
- **Author:** dev.reqistry
- **License:** Unknown
- **Endpoints:** streamable-http https://mcp.reqistry.dev/mcp
- **Source:** https://reqistry.dev
- **Endpoint health:** reachable (last checked 2026-09-21T22:15:10.373Z, 5 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 1 day

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-21T22:15:10.373Z
- **Version scanned:** live
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

13 declared. Observed from a live `tools/list` probe.
- `list_categories` — List all active API categories with the number of published APIs in each. Use to populate a category filter or browse by topic.
- `get_category_apis` — List published APIs in a category by slug (e.g. 'weather', 'finance'). Paginated. Use list_categories first to get a category slug.
- `get_api` — Get full detail for one API by slug or id, including health, metadata, verification, and warnings. Use after browsing a category to drill in.
- `get_alternatives` — Find alternative APIs similar to a given API id — prefers same category, falls back to same API type. limit must be 2 or 3 (default 3).
- `check_health` — Trigger (or return cached) a health check for one API. Returns CACHED within cooldown, or QUEUED with a poll URL. Rate-limited per device.
- `get_api_trust_score` — Get the Reqistry trust score for one API by id or slug. Score covers uptime, response time, docs quality, auth clarity, CORS, pricing clarity, freshness, and Op
- `compare_apis` — Compare 2 to 8 APIs side-by-side by id or slug. Returns auth, pricing, rate limits, SDKs, response time, CORS, verification, OpenAPI, and trust scores.
- `assess_api_production_safety` — Assess whether an API looks production-safe using Reqistry trust score, health, docs, auth, pricing, CORS, and OpenAPI signals.
- `suggest_alternatives` — Suggest healthier alternatives to a weak or dead API. Uses the same category/type matching as Reqistry alternatives.
- `get_change_feed` — Read recent Reqistry API change events: pricing changes, docs moves, OpenAPI changes, health degradation/recovery, and trust-score changes.
- `get_use_case_collections` — Get curated use-case packs such as finance dashboards, free AI APIs, travel apps, and no-auth prototype APIs.
- `submit_api` — Submit a new API for review. Creates a 'pending' submission (not immediately published). At least name or link required. Email optional.
- `recommend_apis` — Get recommended APIs — personalized when the device has bookmarks, otherwise random picks. Optional limit (max 50).

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.reqistry.dev/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/dev.reqistry%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/dev.reqistry%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/dev.reqistry%2Fmcp
- HTML page: https://forgeregistry.com/registry/dev.reqistry%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.