io.github.cyanheads/guardian-mcp-server
NPM · @CYANHEADS/GUARDIAN-MCP-SERVER · SCANNED SEP 22
Guardian Open Platform — search and retrieve full article text from The Guardian archive.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 16 of 49 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 0 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1163 tokens (~387/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (100% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 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
How do I install the io.github.cyanheads/guardian-mcp-server server?
io.github.cyanheads/guardian-mcp-server runs locally as an npm package, launched with npx -y @cyanheads/guardian-mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @cyanheads/guardian-mcp-server
claude mcp add cyanheads-guardian-mcp-server -- npx -y @cyanheads/guardian-mcp-server
{
"mcpServers": {
"cyanheads-guardian-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/guardian-mcp-server"
]
}
}
} {
"servers": {
"cyanheads-guardian-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/guardian-mcp-server"
]
}
}
} codex mcp add cyanheads-guardian-mcp-server -- npx -y @cyanheads/guardian-mcp-server
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"cyanheads-guardian-mcp-server": {
"type": "local",
"command": [
"npx",
"-y",
"@cyanheads/guardian-mcp-server"
],
"enabled": true
}
}
} openclaw mcp add cyanheads-guardian-mcp-server --command npx --arg -y --arg @cyanheads/guardian-mcp-server
mcp_servers:
cyanheads-guardian-mcp-server:
command: "npx"
args: ["-y", "@cyanheads/guardian-mcp-server"] {
"McpServers": {
"cyanheads-guardian-mcp-server": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@cyanheads/guardian-mcp-server"
]
}
}
} assistant mcp add cyanheads-guardian-mcp-server -t stdio -c npx -a -y @cyanheads/guardian-mcp-server
{
"mcpServers": {
"cyanheads-guardian-mcp-server": {
"command": "npx",
"args": [
"-y",
"@cyanheads/guardian-mcp-server"
]
}
}
} 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.
- 22 Sept 26 0
- Stability: 0.80 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: Schema quality not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. functional
- Package version: 0.1.3 → 0.1.4 functional
- 21 Sept 26 −2
- Stability: pass → 0.80 functional
- 20 Sept 26 0
- Stability: 0.97 → pass security
- 19 Sept 26 0
- Stability: pass → 0.97 functional
- 18 Sept 26 0
- Stability: 0.97 → pass security
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −2
- Stability: pass → 0.80 functional
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 22 Sept 2026 · Analysed npm/@cyanheads/guardian-mcp-server@0.1.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 49 packages
| Packages resolved | 49 |
|---|---|
| Stale | 16 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
guardian_browse Browse The Guardian ~482
Browse The Guardian's content by section or tag, or discover available sections and tags for use as filters. Four modes: "section_latest" returns the newest articles from a section (requires section_id); "tag_latest" returns newest articles carrying a tag (requires tag_id); "list_sections" returns all Guardian sections for use as section filters; "list_tags" searches the tag taxonomy (optional: query, tag_type). Start with list_sections or list_tags when you don't know valid section/tag IDs. Powered by The Guardian (open-platform.theguardian.com).
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | yes | Operation mode. "section_latest": newest articles from a section (requires section_id). "tag_latest": newest articles carrying a tag (requires tag_id). "list_sections": return all Guardian sections f… |
| page | integer | – | Page number (1-indexed). Use with total/pages in the response to paginate. |
| page_size | integer | – | Number of results per page (1–50). Applies to all modes. For article-returning modes (section_latest, tag_latest), keep ≤10 to manage context size. |
| query | string | – | For list_tags mode: search term to filter the tag taxonomy (e.g. "climate" to find climate-related tags). For list_sections mode: filter sections by name. Ignored for section_latest and tag_latest. |
| section_id | string | – | Section ID for section_latest mode (e.g. "world", "politics", "science", "environment", "technology", "culture", "sport", "lifeandstyle"). Required for section_latest. Use list_sections first if unsu… |
| tag_id | string | – | Tag ID for tag_latest mode (e.g. "environment/climate-change", "technology/artificial-intelligence", "world/ukraine"). Required for tag_latest. Use list_tags first to discover valid tag IDs. |
| tag_type | string | – | For list_tags mode: restrict to tags of this type. "contributor" returns author profiles. "keyword" returns topic tags (most common). "series" returns article series. "newspaper-book" and "newspaper-… |
| Name | Type | Req | Description |
|---|---|---|---|
| error | object | – | Present when the call failed. Absent on success. |
| mode | string | – | Browse mode that produced this response. "section_latest"/"tag_latest": results[] is populated. "list_sections": sections[] is populated. "list_tags": tags[] is populated. |
| page | integer | – | Current page number. Present for section_latest, tag_latest, and list_tags modes. |
| pages | integer | – | Total pages available. Present for section_latest, tag_latest, and list_tags modes. |
| results | array | – | Recent articles. Populated for section_latest and tag_latest modes. |
| sections | array | – | All Guardian sections. Populated for list_sections mode. |
| tags | array | – | Matching tags. Populated for list_tags mode. |
| total | integer | – | Total items available (articles, sections, or tags). |
| totalCount | integer | – | Total items available (articles, sections, or tags) — discloses how many exist beyond this capped page. |
No examples provided.
guardian_get_article Get Guardian Article ~111
Fetch a single Guardian article by its ID (path slug) with full body text and all metadata. Returns the complete untruncated text for an article ID from guardian_search results. Powered by The Guardian (open-platform.theguardian.com).
| Name | Type | Req | Description |
|---|---|---|---|
| article_id | string | yes | Guardian article ID — the path slug returned in guardian_search results (e.g. "world/2024/mar/01/russia-ukraine-war-latest"). The id field in search results is the correct value to pass here. |
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Full article body text (HTML stripped). Truncated at 2,000 words with a note appended if longer. Returns a placeholder note for galleries, live blogs, and interactives where body is unavailable. |
| byline | string | – | Author attribution (HTML stripped). |
| contributors | array | – | Authors and contributors. |
| error | object | – | Present when the call failed. Absent on success. |
| headline | string | – | Article headline (HTML stripped). |
| id | string | – | Article ID (path slug). |
| pillar_id | string | – | Pillar ID (e.g. "pillar/news", "pillar/sport"). |
| pillar_name | string | – | Pillar display name. |
| published_date | string | – | Publication date and time (ISO 8601 UTC). |
| section_id | string | – | Section identifier. |
| section_name | string | – | Human-readable section name. |
| standfirst | string | – | Sub-headline or article summary (HTML stripped). |
| thumbnail | string | – | Thumbnail image URL. |
| truncated | boolean | – | True when the body was truncated at 2,000 words. |
| type | string | – | Content type (typically "article"). |
| web_url | string | – | URL on theguardian.com. |
| word_count | integer | – | Article word count (absent on galleries, interactives, and some live content). |
No examples provided.
guardian_search Search The Guardian ~468
Full-text search across The Guardian's archive (1999–present) with optional section, tag, contributor, and date filters. Returns articles with full body text (HTML stripped, truncated at 2,000 words). Use guardian_browse with mode=list_sections or mode=list_tags to discover valid filter IDs before searching. Powered by The Guardian (open-platform.theguardian.com).
| Name | Type | Req | Description |
|---|---|---|---|
| contributor | string | – | Restrict to articles by this contributor tag ID (e.g. "profile/george-monbiot"). Contributor IDs follow the pattern "profile/<slug>". Use guardian_browse with mode=list_tags and tag_type=contributor… |
| from_date | string | – | Return only articles published on or after this date. Format: YYYY-MM-DD (e.g. "2024-01-15"). |
| order_by | string | – | Sort order. "relevance" ranks by match strength (default when a query is provided). "newest" and "oldest" sort by publication date. |
| page | integer | – | Page number (1-indexed). Each page returns up to page_size results. |
| page_size | integer | – | Number of results per page (1–50). Keep low (≤10) when requesting full body text to manage context size. Large bodies can be 10–30KB each. |
| query | string | yes | Full-text search query. Supports AND, OR, NOT operators and exact phrases in double quotes. Example: "climate change" AND (policy OR legislation) |
| section | string | – | Restrict results to a section ID (e.g. "world", "politics", "science", "environment", "technology", "culture", "sport", "lifeandstyle"). Use guardian_browse with mode=list_sections to discover valid… |
| tag | string | – | Restrict to content carrying this tag ID (e.g. "environment/climate-change", "technology/artificial-intelligence", "world/ukraine"). Multiple tags separated by commas apply AND logic. Use guardian_br… |
| to_date | string | – | Return only articles published on or before this date. Format: YYYY-MM-DD (e.g. "2024-03-31"). |
| Name | Type | Req | Description |
|---|---|---|---|
| error | object | – | Present when the call failed. Absent on success. |
| notice | string | – | Guidance when the search returned zero results — echoes the query and suggests how to broaden. |
| order_by | string | – | Sort order applied. |
| page | integer | – | Current page number returned. |
| page_size | integer | – | Number of results in this response. |
| pages | integer | – | Total number of pages available. |
| results | array | – | Matching articles. |
| total | integer | – | Total matching articles across all pages. |
| totalCount | integer | – | Total matching articles across all pages — discloses how many results exist beyond this capped page. |
No examples provided.
What is the io.github.cyanheads/guardian-mcp-server server?
io.github.cyanheads/guardian-mcp-server is listed in the public MCP registry as io.github.cyanheads/guardian-mcp-server. Guardian Open Platform, search and retrieve full article text from The Guardian archive. This page covers its npm package (@cyanheads/guardian-mcp-server).
Is the io.github.cyanheads/guardian-mcp-server server safe to use?
io.github.cyanheads/guardian-mcp-server scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. It declares no install or post-install scripts. 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 io.github.cyanheads/guardian-mcp-server server expose?
io.github.cyanheads/guardian-mcp-server exposes 3 tools: guardian_search, guardian_get_article, guardian_browse. Their descriptions and schemas cost roughly 1,061 tokens of context every time the server is loaded.
Is the io.github.cyanheads/guardian-mcp-server server still maintained?
io.github.cyanheads/guardian-mcp-server is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.cyanheads/guardian-mcp-server server under?
io.github.cyanheads/guardian-mcp-server declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.