Persistent Project Context for xAI Grok MCP server
io.github.Wolfe-Jam/grok-faf-mcpWolfe-Jamstreamable-httpv1.8.1Scanned
Persistent project context for xAI Grok. IANA-registered .faf format.
20 tools: 11 change things and 9 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
Anlyon alternative
11 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Persistent Project Context for xAI Grok MCP server can do
The Persistent Project Context for xAI Grok MCP server is published by the GitHub account Wolfe-Jam. It has 20 tools. It can create or change data (11 tools: delta_check, tag_intel, generate_faf_from_github, faf_score and 7 more), but cannot delete data. 9 tools only read.
2 tools bring in text other people can write (generate_faf_from_github and faf_collections_search).
The fixed checks matched 2 findings (install-script and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 16, 2026, version 1.8.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
20 tools
Changes things 11Claude Code: ask
delta_checkDetermine if a topic needs FULL, DELTA, or X-DELTA soul.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Determine if a topic needs FULL, DELTA, or X-DELTA soul.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_business_cardPrint a business card for an agent from its own name, description, colour and picture.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Print a business card for an agent from its own name, description, colour and picture. Returns the agent's .fafa (FAF Agent file) and a link that opens its card. Nothing is stored: the .fafa travels in the link. The card says "self-declared" because nothing is checked against a repo.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_estimate_tokensEstimate token count for arbitrary content via the Zig WASM engine.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_gatePhase III (FRC) — pre-promotion quality gate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Phase III (FRC) — pre-promotion quality gate. Scores .faf content (edge Mk4) + estimates tokens and returns a deterministic promote/hold verdict BEFORE it goes to a Grok Collection. Promote IFF score >= min_score AND tokens <= max_tokens (defaults 85/8000). Edge parity with the local gate; the hold-hint can't list empty slots at the edge.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_memoryPhase III (FRC) — query the durable .fafm model by type/tag/priority/text.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Phase III (FRC) — query the durable .fafm model by type/tag/priority/text. Omit filters for a structured summary. .fafm is NOT scored: this SELECTS facts (provenance preserved), never grades them.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_orchestrate_recommendationTakes raw content strings (`.faf`, `.fafm`, and optionally `package.json`/`CHANGELOG.md`/`README.md`) and runs deterministic drift + contradiction signals across the FAF substrate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Takes raw content strings (`.faf`, `.fafm`, and optionally `package.json`/`CHANGELOG.md`/`README.md`) and runs deterministic drift + contradiction signals across the FAF substrate. Returns a structured `Recommendation` (recommend, severity, reason, summary) with `hints` containing the current `effective_policy` and `partial[]` for any stateful signals unavailable on the current surface. Light-lane execution (hosted) is WASM-pure with no filesystem access. Heavy-lane execution (local via bunx/rust-faf-mcp) has full FS + persisted state. Advisory only — never auto-fires.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_scoreScore .faf YAML content with the always-33 faf-kernel (WASM).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Score .faf YAML content with the always-33 faf-kernel (WASM). Returns 0-100 (capped). The same score faf-cli and every FAF MCP give. Runs at the edge.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_sectionPhase III (FRC) — returns an EXACT, WHOLE .faf section by dotted path (e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Phase III (FRC) — returns an EXACT, WHOLE .faf section by dotted path (e.g. "stack", "human_context"), structure preserved — the deterministic complement to blind chunking. Omit "section" to list every path.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
generate_faf_from_githubGenerate a .faf file from any public GitHub repository WITHOUT cloning.Reads text others write1 finding
Why it is in this group
- The name "generate_faf_from_github" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "generate_faf_from_github" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_faf_from_github" says "generate": a word for a change.
Description, as the server wrote it Generate a .faf file from any public GitHub repository WITHOUT cloning. Extracts 6 Ws from README, analyzes stack from languages and package.json, and generates Championship-grade AI context. Returns .faf content, quality score, and metadata.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
refresh_fafRe-ground on .faf content — re-score with the always-33 faf-kernel (33 slots; slotignored slots drop out), report drift vs an optional baseline score, and return a stamped re-groun…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Re-ground on .faf content — re-score with the always-33 faf-kernel (33 slots; slotignored slots drop out), report drift vs an optional baseline score, and return a stamped re-ground. The explicit re-grounding primitive for long sessions: drift → refresh → re-grounded. Built for Grok, by request.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
tag_intelDiscover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 9Show 9 read-only tools
faf_analyzeOne-call composite — returns score, tier-ready, valid, and engine identifier.No findings
Why it is in this group
- The name "faf_analyze" says "analyze": a word for reading.
Description, as the server wrote it One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_collections_searchPhase III (FRC §7b) — semantic search over a Grok Collection at the edge, KV-cached (1h TTL).Reads text others writeNo findings
Why it is in this group
- The name "faf_collections_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Phase III (FRC §7b) — semantic search over a Grok Collection at the edge, KV-cached (1h TTL). Returns matched chunks (content, score, file). Requires the XAI_API_KEY secret; composes with faf_section (structural) for hybrid retrieval. Handled env-aware in the MCP handler (needs the key + KV).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
faf_get_tierResolve the FAF tier for a given numeric score.No findings
Why it is in this group
- The name "faf_get_tier" says "get": a word for reading.
Description, as the server wrote it Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
faf_validateValidate .faf YAML content: true if mission-ready (always-33 score of 100).No findings
Why it is in this group
- The name "faf_validate" says "validate": a word for reading.
Description, as the server wrote it Validate .faf YAML content: true if mission-ready (always-33 score of 100).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_soulFetch a context soul by name.No findings
Why it is in this group
- The name "get_soul" says "get": a word for reading.
Description, as the server wrote it Fetch a context soul by name. Returns structured AI context.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_soulsList context souls: showcase souls first, then claimed souls.No findings
Why it is in this group
- The name "list_souls" says "list": a word for reading.
Description, as the server wrote it List context souls: showcase souls first, then claimed souls. Paged: pass the returned cursor for more.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_tagsList all unique tags used in a soul, with counts.No findings
Why it is in this group
- The name "list_tags" says "list": a word for reading.
Description, as the server wrote it List all unique tags used in a soul, with counts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_by_tagFind all entries in a soul with a specific tag.No findings
Why it is in this group
- The name "search_by_tag" says "search": a word for reading.
Description, as the server wrote it Find all entries in a soul with a specific tag.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_contextFull-text search across souls (showcase first, then claimed souls; [private] sections are never searched).No findings
Why it is in this group
- The name "search_context" says "search": a word for reading.
Description, as the server wrote it Full-text search across souls (showcase first, then claimed souls; [private] sections are never searched). Returns matching lines only. Searches a page of souls per call: pass the returned cursor for more.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:01 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcpaas.live/.well-known/oauth-protected-resource
- Authorization servers
- https://dev-bwqyzb3erxhmxdok.us.auth0.com/
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- no
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcpaas.live/grok/mcp/v1: tools/list returned 20 tools to an anonymous client, including delta_check (write), tag_intel (write), generate_faf_from_github (write), faf_score (write), faf_estimate_tokens (write) and 6 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "generate_faf_from_github" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "generate_faf_from_github" says "generate": a word for a change.
- InfoThe whole server
The package.json has a "postinstall" script, which npm runs on install.
What this check looks forMatched text
scripts.postinstall: "node scripts/postinstall.js"
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:list_soulsOnly readsdescriptioninputSchema
- Changed:search_contextOnly readsdescriptioninputSchema
Install
Pinned to version 1.8.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http grok-faf https://mcpaas.live/grok/mcp/v1claude mcp add --transport http grok-faf https://mcpaas.live/grok/mcp/v1Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__grok-faf__get_soul",
"mcp__grok-faf__list_souls",
"mcp__grok-faf__list_tags",
"mcp__grok-faf__search_by_tag",
"mcp__grok-faf__search_context",
"mcp__grok-faf__faf_validate",
"mcp__grok-faf__faf_get_tier",
"mcp__grok-faf__faf_analyze",
"mcp__grok-faf__faf_collections_search"
],
"ask": [
"mcp__grok-faf__delta_check",
"mcp__grok-faf__tag_intel",
"mcp__grok-faf__generate_faf_from_github",
"mcp__grok-faf__faf_score",
"mcp__grok-faf__faf_estimate_tokens",
"mcp__grok-faf__refresh_faf",
"mcp__grok-faf__faf_orchestrate_recommendation",
"mcp__grok-faf__faf_gate",
"mcp__grok-faf__faf_section",
"mcp__grok-faf__faf_memory",
"mcp__grok-faf__faf_business_card"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as grok-faf. Review it before you use it.
Capability tags behind 2 rules
- mcp__grok-faf__generate_faf_from_github untrusted-input
- mcp__grok-faf__faf_collections_search untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Wolfe-Jam/grok-faf-mcp/verify?hash=08cc20ef57033ad5b81cbb6ea5d9bf2af7b56380346dff92f41cf42267c57734" | jq -e '.changed == false'Pinned hash 08cc20ef5703, from Nov 16, 2026, 07:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Wolfe-Jam/grok-faf-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Wolfe-Jam/grok-faf-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:22 UTC.
Persistent Project Context for xAI Grok MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Persistent Project Context for xAI Grok MCP server safe?
- No scan can promise that. What its definitions show: 20 tools, 11 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Persistent Project Context for xAI Grok MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Persistent Project Context for xAI Grok MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Persistent Project Context for xAI Grok MCP server have?
- 20 tools: 11 write, 9 read. delta_check, tag_intel, generate_faf_from_github, faf_score, faf_estimate_tokens, refresh_faf, faf_orchestrate_recommendation, faf_gate and 12 more.
Does the Persistent Project Context for xAI Grok MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Persistent Project Context for xAI Grok MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Persistent Project Context for xAI Grok MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.