# io.github.Franksterino/citeguard

> Verify citations in AI text: fetches each cited source, returns verdicts with evidence quotes.

- name: io.github.Franksterino/citeguard
- version: 0.1.2
- connection class: R0 (autonomous)
- trust: 86/100
- quality: 71/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Franksterino%2Fciteguard
- tools: https://api.protogrid.dev/v1/servers/io.github.Franksterino%2Fciteguard/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "citeguard": {
      "type": "http",
      "url": "https://citeguard.boundy.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 97
- freshness: 65
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-92% ~updated-106d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 71/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 71 (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
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_links (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_document (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); verify_claims (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 324 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: 33 (weight 15)

- fail `deps.known_vulns`: 9 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-23hp-3jrh-7fpw in tar@6.2.1 (indirect, fixed in 7.5.19), GHSA-34x7-hfp2-rc4v in tar@6.2.1 (indirect, fixed in 7.5.7), GHSA-83g3-92jg-28cx in tar@6.2.1 (indirect, fixed in 7.5.8), ...; 5 more of lower severity or without a fix
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 3 known advisories (GHSA-22jm-h49p-29qw, GHSA-6prh-2h8m-c8cw, GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.32.0 or later
- pass `deps.resolvable`: citeguard@0.1.2 resolved: 177 packages

- tools: 3, about 324 tokens to load them all
- tool set hash: fce177c00ffa7925275e644da8693a3e
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Franksterino/citeguard.svg)](https://protogrid.dev/servers/io.github.Franksterino/citeguard)
- 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._

## Dependencies

- npm citeguard@0.1.2: resolved, 176 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-23hp-3jrh-7fpw (critical) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.19 ``, advisory summary: "node-tar: Decompression/parse DoS via unlimited input" https://osv.dev/vulnerability/GHSA-23hp-3jrh-7fpw
  - GHSA-22jm-h49p-29qw (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.32.0 ``, advisory summary: "MCP TypeScript SDK: Experimental tasks were not tied to the session that created them" https://osv.dev/vulnerability/GHSA-22jm-h49p-29qw
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h
  - GHSA-34x7-hfp2-rc4v (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.7 ``, advisory summary: "node-tar Vulnerable to Arbitrary File Creation/Overwrite via Hardlink Path Traversal" https://osv.dev/vulnerability/GHSA-34x7-hfp2-rc4v
  - GHSA-83g3-92jg-28cx (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.8 ``, advisory summary: "Arbitrary File Read/Write via Hardlink Target Escape Through Symlink Chain in node-tar Extraction" https://osv.dev/vulnerability/GHSA-83g3-92jg-28cx
  - GHSA-8qq5-rm4j-mr97 (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.3 ``, advisory summary: "node-tar is Vulnerable to Arbitrary File Overwrite and Symlink Poisoning via Insufficient Path Sanitization" https://osv.dev/vulnerability/GHSA-8qq5-rm4j-mr97
  - GHSA-8x88-c5mf-7j5w (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.18 ``, advisory summary: "node-tar: Negative tar entry size causes infinite loop in archive replace" https://osv.dev/vulnerability/GHSA-8x88-c5mf-7j5w
  - GHSA-9ppj-qmqm-q256 (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.11 ``, advisory summary: "node-tar Symlink Path Traversal via Drive-Relative Linkpath" https://osv.dev/vulnerability/GHSA-9ppj-qmqm-q256
  - GHSA-qffp-2rhf-9h96 (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.10 ``, advisory summary: "tar has Hardlink Path Traversal via Drive-Relative Linkpath" https://osv.dev/vulnerability/GHSA-qffp-2rhf-9h96
  - GHSA-r292-9mhp-454m (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.21 ``, advisory summary: "node-tar: Uncontrolled recursion in mapHas/filesFilter allows uncatchable stack-overflow DoS via crafted long-path tar with member selection" https://osv.dev/vulnerability/GHSA-r292-9mhp-454m
  - GHSA-r6q2-hw4h-h46w (high) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.4 ``, advisory summary: "Race Condition in node-tar Path Reservations via Unicode Ligature Collisions on macOS APFS" https://osv.dev/vulnerability/GHSA-r6q2-hw4h-h46w
  - GHSA-6prh-2h8m-c8cw (moderate) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.32.0 ``, advisory summary: "MCP TypeScript client SDK: HTTP client transports and OAuth requests followed cross-origin redirects and re-sent custom headers and request bodies" https://osv.dev/vulnerability/GHSA-6prh-2h8m-c8cw
  - GHSA-5r4p-p66f-jhc7 (moderate) in `` hono@4.13.9 ``, indirect, fixed in `` 4.13.11 ``, advisory summary: "Hono: \`serveStatic\` decodes the request path a second time, leading to bypass of middleware on static paths" https://osv.dev/vulnerability/GHSA-5r4p-p66f-jhc7
  - GHSA-gvwx-54wh-qm9j (moderate) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.17 ``, advisory summary: "node-tar: Uncaught Exception DoS via NUL byte in PAX path/linkpath records" https://osv.dev/vulnerability/GHSA-gvwx-54wh-qm9j
  - GHSA-vmf3-w455-68vh (moderate) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.16 ``, advisory summary: "node-tar applies PAX size override to intermediary GNU long-name/long-link headers, causing tar parser interpretation differential (file smuggling)" https://osv.dev/vulnerability/GHSA-vmf3-w455-68vh
  - GHSA-w8wr-v893-vjvp (moderate) in `` tar@6.2.1 ``, indirect, fixed in `` 7.5.18 ``, advisory summary: "node-tar: Process crash via PAX numeric path type confusion" https://osv.dev/vulnerability/GHSA-w8wr-v893-vjvp
  - GHSA-3p6v-hrg8-8qj7 (low) in `` @mozilla/readability@0.5.0 ``, direct, fixed in `` 0.6.0 ``, advisory summary: "@mozilla/readability Denial of Service through Regex" https://osv.dev/vulnerability/GHSA-3p6v-hrg8-8qj7

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://citeguard.boundy.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.9189189)

## Packages

- npm citeguard@0.1.2 secrets: CITEGUARD_JUDGE_KEY

## Tools (3)

- `check_document`: Audit every citation in a markdown/plain-text document: extracts claim+source pairs (markdown links, footnotes, DOIs, bare URLs), verifies each against the fetched source, and returns a report with a citation integrity score (0-100).
- `check_links`: Liveness-only check (no LLM): extracts all cited URLs and reports dead links, homepage redirects, and archive.org availability.
- `verify_claims`: Verify claim+source pairs: fetches each cited URL and returns a per-claim verdict (supported / partially_supported / contradicted / unsupported / uncertain / could_not_fetch) with a quoted evidence span from the source.