Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Persistent Project Context for xAI Grok

REMOTE · MCPAAS.LIVE · 2 COMPONENTS

Persistent project context for xAI Grok. IANA-registered .faf format.

0 this week 87 Trust /100

Last scanned (2 hours ago)

Scores higher than 94% of remote servers

Reachable. Last reached 5 Nov 2026.

Deprecated

This server is marked deprecated in the MCP registry.

Trust breakdown (7 categories)

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 Security74
Transport & Reachability100
Schema Quality & AI Usability84
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2122 tokens (~73/item across 29 items; 20 tools + 9 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 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
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 22 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
Changelog

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.

  • 5 Nov 26 0
    • Tool “search_context” rewrote its description, which is the text the model reads security
    • Tool “list_souls” rewrote its description, which is the text the model reads security
    • Server version: mcpaas-cf@1.11.9 → mcpaas-cf@1.11.14 functional
    • “list_souls” added an optional parameter “limit” cosmetic
    • “list_souls” added an optional parameter “cursor” cosmetic
    • “search_context” added an optional parameter “cursor” cosmetic
    • “search_context” added an optional parameter “limit” cosmetic
    • “search_context” reworded the description of “soul” cosmetic
  • 4 Nov 26 0
    • Server version: mcpaas-cf@1.11.7 → mcpaas-cf@1.11.9 functional
  • 1 Nov 26 0
    • Server version: mcpaas-cf@1.11.6 → mcpaas-cf@1.11.7 functional
  • 31 Oct 26 0
    • Server version: mcpaas-cf@1.11.4 → mcpaas-cf@1.11.6 functional
  • 30 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: mcpaas-cf@1.11.3 → mcpaas-cf@1.11.4 functional
  • 20 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • MCP protocol: Implements a current MCP spec version (2026-07-28). functional
    • MCP protocol version: 2025-11-25 → 2026-07-28 functional
    • Server version: mcpaas-cf@1.11.1 → mcpaas-cf@1.11.3 functional
  • 18 Oct 26 0
    • Server version: mcpaas-cf@1.11.0 → mcpaas-cf@1.11.1 functional
  • 17 Oct 26 0
    • Schema quality: 1635 → 1838 ▼ functional
    • Server version: mcpaas-cf@1.8.13 → mcpaas-cf@1.11.0 functional
    • New tool “faf_business_card” functional
Diagnostics

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 5 Nov 2026 · Probed https://mcpaas.live/grok/mcp/v1

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcpaas.live CN=WE1,O=Google Trust Services,C=US 8 Sept 2026 7 Dec 2026 ECDSA 256 ECDSA-SHA256 8d37294707672d33135102509b0ab759
SANs: mcpaas.live
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 mcpaas.live. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
live. present 4724, 36322 8, 8 Verified
mcpaas.live. absent 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://mcpaas.live/grok/mcp/v1 Verified 200
http (plaintext) http://mcpaas.live/grok/mcp/v1 HTTPS enforced 301 https://mcpaas.live/grok/mcp/v1
MCP tools · 20 exposed · ~1,832 tokens

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 →

Tool Tokens
delta_check ~35

Determine if a topic needs FULL, DELTA, or X-DELTA soul.

NameTypeReqDescription
topicstringyesTopic to check

No output schema declared.

No examples provided.

faf_analyze ~49

One-call composite — returns score, tier-ready, valid, and engine identifier. Two WASM calls, sub-millisecond total.

NameTypeReqDescription
contentstringyesRaw .faf YAML content to analyze.

No output schema declared.

No examples provided.

faf_business_card ~203

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.

NameTypeReqDescription
accentstring–The card colour as a hex, e.g. "#7c3aed". Optional; none means ink (black or white).
descriptionstring–What the agent does, in one line, up to 140 characters. Optional.
iconstring–An https link to a picture for the logo spot, e.g. "https://example.com/me.png". Optional; none means the monogram. A square PNG (256 x 256, transparent background) or an SVG looks best.
namestringyesThe agent's name, up to 100 characters.

No output schema declared.

No examples provided.

faf_collections_search ~125

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).

NameTypeReqDescription
collection_idstringyesThe Grok Collection id to search.
limitnumber–Max chunks to return (default 5).
querystringyesThe search query.

No output schema declared.

No examples provided.

faf_estimate_tokens ~48

Estimate token count for arbitrary content via the Zig WASM engine. Sub-millisecond, zero allocations. Useful for context-budget planning.

NameTypeReqDescription
contentstringyesContent to estimate tokens for.

No output schema declared.

No examples provided.

faf_gate ~136

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.

NameTypeReqDescription
contentstringyesRaw .faf YAML content to gate.
max_tokensnumber–Maximum tokens to promote (default 8000).
min_scorenumber–Minimum score to promote (default 85).

No output schema declared.

No examples provided.

faf_get_tier ~55

Resolve the FAF tier for a given numeric score. Returns the tier symbol (Trophy/Gold/Silver/Bronze/etc.) per the canonical tier-table.

NameTypeReqDescription
scorenumberyesNumeric score 0-100.

No output schema declared.

No examples provided.

faf_memory ~130

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.

NameTypeReqDescription
contentstringyesRaw .fafm YAML content.
prioritystring–Filter by priority (e.g. "critical").
querystring–Case-insensitive substring match on fact text.
tagstring–Filter by a tag.
typestring–Filter by fact type (e.g. "feedback").

No output schema declared.

No examples provided.

faf_orchestrate_recommendation ~253

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.

NameTypeReqDescription
changelogstring–Raw CHANGELOG.md content. Enables changelog cross-stamp checks.
fafstring–Raw .faf YAML content (project DNA). Required for any meaningful analysis.
fafmstring–Raw .fafm YAML content (memory layer). Enables drift detection.
packageJsonstring–Raw package.json content. Enables version cross-stamp checks (.faf vs pkg).
readmestring–Raw README.md content. Enables README arch-tree cross-stamp checks.

No output schema declared.

No examples provided.

faf_score ~74

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.

NameTypeReqDescription
contentstringyesRaw .faf YAML content. Souls with a [faf] section have it extracted automatically.

No output schema declared.

No examples provided.

faf_section ~97

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.

NameTypeReqDescription
contentstringyesRaw .faf YAML content.
sectionstring–Dotted path to retrieve (e.g. "stack.backend"). Omit to list all paths.

No output schema declared.

No examples provided.

faf_validate ~41

Validate .faf YAML content: true if mission-ready (always-33 score of 100).

NameTypeReqDescription
contentstringyesRaw .faf YAML content to validate.

No output schema declared.

No examples provided.

generate_faf_from_github ~92

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.

NameTypeReqDescription
repostringyesGitHub repository URL or owner/repo format (e.g., "facebook/react" or "https://github.com/facebook/react")

No output schema declared.

No examples provided.

get_soul ~46

Fetch a context soul by name. Returns structured AI context.

NameTypeReqDescription
soulstringyesSoul identifier (e.g., "spacex", "wolfe", "grok")

No output schema declared.

No examples provided.

list_souls ~62

List context souls: showcase souls first, then claimed souls. Paged: pass the returned cursor for more.

NameTypeReqDescription
cursorstring–Cursor from the previous page
limitnumber–Souls per page (default 50, max 100)

No output schema declared.

No examples provided.

list_tags ~29

List all unique tags used in a soul, with counts.

NameTypeReqDescription
soulstringyesSoul identifier

No output schema declared.

No examples provided.

refresh_faf ~153

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.

NameTypeReqDescription
baselinenumber–Optional last-known score (0-100). When provided, the drift delta (current - baseline) is reported.
contentstringyesRaw .faf YAML content to re-ground on.
verbatimboolean–When true, return the full .faf content verbatim with the stamp. Default false (stamped delta + summary).

No output schema declared.

No examples provided.

search_by_tag ~40

Find all entries in a soul with a specific tag.

NameTypeReqDescription
soulstringyesSoul identifier
tagstringyesTag to search for

No output schema declared.

No examples provided.

search_context ~112

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.

NameTypeReqDescription
cursorstring–Cursor from the previous call
limitnumber–Souls searched per call (default 25, max 50)
querystringyesText to search for
soulstring–Specific soul (optional, searches a page of all souls if omitted)

No output schema declared.

No examples provided.

tag_intel ~52

Discover tag patterns, co-occurrence, candidates, and merge suggestions across all namepoints. Optionally suggest tags for a specific handle.

NameTypeReqDescription
handlestring–Optional: suggest tags for this specific namepoint

No output schema declared.

No examples provided.

Install

How do I install the Persistent Project Context for xAI Grok MCP server?

Persistent Project Context for xAI Grok is a hosted endpoint at https://mcpaas.live/grok/mcp/v1, 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 · mcpaas.live

# add to Claude Code
claude mcp add --transport http wolfe-jam-grok-faf-mcp 'https://mcpaas.live/grok/mcp/v1'
Common questions

What is the Persistent Project Context for xAI Grok MCP server?

Persistent Project Context for xAI Grok is an MCP server listed in the public MCP registry as io.github.Wolfe-Jam/grok-faf-mcp. Persistent project context for xAI Grok. IANA-registered .faf format. This page covers its hosted endpoint (https://mcpaas.live/grok/mcp/v1).

Is the Persistent Project Context for xAI Grok MCP server safe to use?

Persistent Project Context for xAI Grok scores 87 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 Persistent Project Context for xAI Grok MCP server expose?

Persistent Project Context for xAI Grok exposes 20 tools: get_soul, list_souls, delta_check, list_tags, search_by_tag, and 15 more. Their descriptions and schemas cost roughly 1,832 tokens of context every time the server is loaded.

Does the Persistent Project Context for xAI Grok MCP server require authentication?

No. We connected to Persistent Project Context for xAI Grok without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Persistent Project Context for xAI Grok MCP server still maintained?

Persistent Project Context for xAI Grok is marked deprecated in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.