# The MCP Census

> Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK.

- name: com.mcpcensus/census
- version: 1.4.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 94/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.mcpcensus%2Fcensus
- tools: https://api.protogrid.dev/v1/servers/com.mcpcensus%2Fcensus/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "census": {
      "type": "http",
      "url": "https://api.mcpcensus.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-96% ~updated-51d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 94/100 (strong)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 4 of 15 tools declare readOnlyHint or destructiveHint
- warn `tools.directory_hints`: 4 of 15 tools declare all four hints; missing: census_watch_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); census_watch_unsubscribe (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); census_recent (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,157 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 15, about 2,157 tokens to load them all
- tool set hash: 49f84e8281a03465186578d1c234ff26
- badge: [![protogrid quality](https://protogrid.dev/badge/com.mcpcensus/census.svg)](https://protogrid.dev/servers/com.mcpcensus/census)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://api.mcpcensus.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

_none_

## Tools (15)

- `census_audit_config`: Audit a whole MCP client config in one call (.mcp.json, claude_desktop_config.json, .cursor/mcp.json, .vscode/mcp.json, Codex config.toml text). Resolves every entry without guessing (url → remote_url, npx → npm package, uvx → PyPI package) and returns one PASS / REVIEW / BLOCK / UNKNOWN verdict per entry under a built-in policy, plus CENSUS-AUDIT/1 text, valid_until_epoch and exit_code (1 on any BLOCK). UNKNOWN is never upgraded to PASS. Cost 1 credit per config per UTC day; keyless callers get one config of ≤25 entries per IP per day. Not a malware scan; PASS is not a sandbox. Strip env/headers before sending.
- `census_changes`: The Census change feed (CENSUS-CHANGES/1): observed transitions across every server — server_new, remote_down, remote_up, tools_changed, health_change, verified_change, security, endpoint_moved, registry_status, spec_era_change. Cursor-paginated: pass next_cursor back as since. Filter by events, server_names or namespace_domain. Only real transitions, never 'still fine'. Unmetered in v1; poll hourly. Not a malware scan.
- `census_coverage`: Public transparency report (same payload as GET /v1/coverage). Unmetered. Live D1 census/identity/remote/protocol/adoption/pipeline counts plus method notes — never invents completeness percentages or a brand_audit punch list.
- `census_credits`: Show remaining Census credits for this API key (wallet after the UTC-month grant). Unmetered. Without a key, returns anonymous unique-per-day remaining — not a wallet.
- `census_lookalikes`: Contested identity for one exact server_name: official_for, name_collision_count, and up to 10 other census server_name values sharing the same namespace brand or tail. Never invents lookalikes. Cost 1.
- `census_lookup`: Get the live health verdict for one MCP server by its exact registry name (e.g. 'io.github.owner/name'). Returns stars, last-push recency, gone/archived/deprecated flags, name-collision count, and a fact-based health verdict (healthy | issues | unknown).
- `census_policy_list`: List the exact immutable Preflight v1 built-in policy objects, canonical ruleset, and policy digests. Unmetered.
- `census_preflight`: Evaluate one exact MCP server under a documented built-in install policy. Returns PASS, REVIEW, or BLOCK with evidence reasons, freshness, digests, and explicit limits. This is a first gate, not a security audit. refresh=if_stale requires x-api-key.
- `census_recent`: Newest MCP servers by real first_seen_at (same payload as GET /v1/recent). Unmetered. Only rows with a known first-seen date — never invents or guesses discovery times. Optional limit 1–50 (default 20).
- `census_search`: Search MCP servers by keyword or partial name (e.g. 'github', 'postgres'). Returns ranked matches with health/trust. Also returns: resolved_query (auto typo fix), disambiguate (when unsure), known_brand (we recognize a strong product but it has no official MCP — e.g. CodeRabbit), research (watchlist/confirmed_absent), query_intent (brand_lookup|category|package|install_gate|junk — does not change ranking), intent_cta (preflight when they asked an install-gate question). Prefer official_match=true rows. Never invent servers.
- `census_stamp`: Census stamp for one exact MCP server under a built-in policy. Same input as census_preflight. Returns the preflight body plus compact CENSUS-STAMP/1 text and stamp_json. Cost matches preflight. Never connect without a stamp. PASS is not a malware scan or permission review.
- `census_stats`: Ecosystem headline numbers from the live census (same payload as GET /v1/stats). Unmetered. Returns total servers, healthy/issues counts, popular (gh_stars>=1000), remote-capable count, github-linked count, and captured_at. No invented metrics.
- `census_watch_list`: List active per-server watches for this API key. Requires x-api-key.
- `census_watch_subscribe`: Subscribe this agent (or a human email) to alerts for ONE specific MCP server. Fires only on real observed changes: remote_down, remote_up, health_change, verified_change, security. Requires x-api-key. Prefer webhook_url (https) so your agent can receive POST callbacks; email optional. Returns a watch id + HMAC secret (X-Census-Signature: sha256=…). Free tier: 5 watches; pro: 50.
- `census_watch_unsubscribe`: Deactivate a watch by id. Requires x-api-key that owns the watch.