The MCP Census
REMOTE · API.MCPCENSUS.COM
Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK.
Available components
Last scanned (22 hours ago)
Scores higher than 61% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Security
Recent critical change
Authorization (1 Nov 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (census_watch_unsubscribe). See how to fix → View diagnostics → Fail
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1595 tokens (~106/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 74% of tool parameters carry a description.Partial
- Structured output schemas are declared (13% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (12)
- TLS certificate
- Authorization
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 9 Nov 26 +1
- Stability: 0.97 → pass security
- 8 Nov 26 −1
- Stability: pass → 0.97 functional
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 1 Nov 26 0
- Authorization: unverified → fail ▼ critical
- Tool “census_watch_unsubscribe” is now declared destructive security
- Tool “census_audit_config” changed its title: Audit an MCP client config cosmetic
- Tool “census_changes” changed its title: Census change feed cosmetic
- Tool “census_coverage” changed its title: Census coverage report cosmetic
- Tool “census_credits” changed its title: Show remaining Census credits cosmetic
- Tool “census_lookalikes” changed its title: Find lookalike MCP servers cosmetic
- Tool “census_lookup” changed its title: Look up an MCP server cosmetic
- Tool “census_policy_list” changed its title: List MCP Census policies cosmetic
- Tool “census_preflight” changed its title: Run MCP server preflight cosmetic
- Tool “census_recent” changed its title: Recently discovered MCP servers cosmetic
- Tool “census_search” changed its title: Search MCP servers cosmetic
- Tool “census_stamp” changed its title: Census stamp for an MCP server cosmetic
- Tool “census_stats” changed its title: Census ecosystem stats cosmetic
- Tool “census_watch_list” changed its title: List my server watches cosmetic
- Tool “census_watch_subscribe” changed its title: Watch an MCP server for changes cosmetic
- Tool “census_watch_unsubscribe” changed its title: Remove a server watch cosmetic
- 29 Sept 26 0
- Stability: 0.97 → pass security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 20 Sept 26 0
- Tool “census_search” rewrote its description, which is the text the model reads security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://api.mcpcensus.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcpcensus.com | CN=WE1,O=Google Trust Services,C=US | 10 Nov 2026 | 8 Feb 2027 | ECDSA 256 | ECDSA-SHA256 | 430ecbdef301c17d0e8d35c9b4e0ea92 |
| SANs: mcpcensus.com, api.mcpcensus.com, *.api.mcpcensus.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.mcpcensus.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| mcpcensus.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.mcpcensus.com/mcp | Verified | 200 | |
| http (plaintext) | http://api.mcpcensus.com/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
census_audit_config Audit an MCP client config ~265
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.
| Name | Type | Req | Description |
|---|---|---|---|
| config | – | yes | The config document: an object with mcpServers | servers | mcp_servers, a list under entries[], or raw text (JSON or Codex config.toml) |
| format | string | – | – |
| policy_id | string | – | – |
| previous_tools_digests | object | – | alias → tools_digest from your last audit; sets tools_drift per entry |
| strict | boolean | – | exit_code 2 when any entry is REVIEW or UNKNOWN |
No output schema declared.
No examples provided.
census_changes Census change feed ~191
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.
| Name | Type | Req | Description |
|---|---|---|---|
| events | array | – | Event names to include (default all) |
| limit | integer | – | – |
| namespace_domain | string | – | Registrable domain of a DNS-verified namespace, e.g. notion.com |
| server_names | array | – | Exact canonical names to include (≤50) |
| since | string | – | next_cursor from the previous page, or an RFC 3339 time for the first call |
No output schema declared.
No examples provided.
census_coverage Census coverage report ~59
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
census_credits Show remaining Census credits ~44
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
census_lookalikes Find lookalike MCP servers ~69
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.
| Name | Type | Req | Description |
|---|---|---|---|
| server_name | string | yes | Exact canonical Census server name |
No output schema declared.
No examples provided.
census_lookup Look up an MCP server ~79
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).
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | Exact MCP registry server name |
No output schema declared.
No examples provided.
census_policy_list List MCP Census policies ~35
List the exact immutable Preflight v1 built-in policy objects, canonical ruleset, and policy digests. Unmetered.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| audit_signed | – | yes | – |
| ok | – | yes | – |
| policies | array | yes | – |
| policy_digests | object | yes | – |
| ruleset | object | yes | – |
No examples provided.
census_preflight Run MCP server preflight ~91
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.
| Name | Type | Req | Description |
|---|---|---|---|
| policy_id | string | – | – |
| refresh | string | – | – |
| server_name | string | yes | Exact canonical Census server name |
| Name | Type | Req | Description |
|---|---|---|---|
| audit_id | string|null | yes | – |
| audit_signed | – | yes | – |
| decision | string | yes | – |
| decision_input_digest | string | yes | – |
| decision_scope | – | yes | – |
| engine_version | string | yes | – |
| evaluated_at | string | yes | – |
| facts | object | yes | – |
| facts_digest | string | yes | – |
| limitations | array | yes | – |
| meaning | string | yes | – |
| ok | – | yes | – |
| policy | object | yes | – |
| reasons | array | yes | – |
| server_name | string | yes | – |
| valid_until | string | yes | – |
No examples provided.
census_recent Recently discovered MCP servers ~78
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).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results 1–50 (default 20) |
No output schema declared.
No examples provided.
census_search Search MCP servers ~171
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results 1–50 (default 20) |
| query | string | yes | Keyword or partial server name (>= 2 chars). Typos and space variants are resolved when confident. |
No output schema declared.
No examples provided.
census_stamp Census stamp for an MCP server ~96
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.
| Name | Type | Req | Description |
|---|---|---|---|
| policy_id | string | – | – |
| refresh | string | – | – |
| server_name | string | yes | Exact canonical Census server name |
No output schema declared.
No examples provided.
census_stats Census ecosystem stats ~65
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
census_watch_list List my server watches ~24
List active per-server watches for this API key. Requires x-api-key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
census_watch_subscribe Watch an MCP server for changes ~189
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.
| Name | Type | Req | Description |
|---|---|---|---|
| string | – | Optional human email for the same alerts | |
| events | array | – | Subset of remote_down,remote_up,health_change,verified_change,security,tools_changed (default: all) |
| label | string | – | Optional agent-chosen label |
| server_name | string | yes | Exact registry name to watch |
| webhook_url | string | – | https URL that will receive signed POST event payloads |
No output schema declared.
No examples provided.
census_watch_unsubscribe Remove a server watch ~40
Deactivate a watch by id. Requires x-api-key that owns the watch.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Watch id from census_watch_subscribe |
No output schema declared.
No examples provided.
How do I install the The MCP Census server?
The MCP Census is a hosted endpoint at https://api.mcpcensus.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.mcpcensus.com
claude mcp add --transport http com-mcpcensus-census 'https://api.mcpcensus.com/mcp'
What is the The MCP Census server?
The MCP Census is listed in the public MCP registry as com.mcpcensus/census. Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK. This page covers its hosted endpoint (https://api.mcpcensus.com/mcp).
Is the The MCP Census server safe to use?
The MCP Census scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the The MCP Census server expose?
The MCP Census exposes 15 tools: census_lookup, census_search, census_stats, census_recent, census_coverage, and 10 more. Their descriptions and schemas cost roughly 1,496 tokens of context every time the server is loaded.
Does the The MCP Census server require authentication?
No. We connected to The MCP Census without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the The MCP Census server still maintained?
The MCP Census is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the The MCP Census server?
VerifyMCP ran 12 checks on The MCP Census, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about The MCP Census: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.