Skip to main content
Glama
Wolfe-Jam

.FAF Context

by Wolfe-Jam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to .FAF Context

Related Servers

  • contextforge-mcp

    alfredoizdev
    A
    license
    A
    quality
    C
    maintenance
    Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based, Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot. Semantic search, Git sync, project-based organization, and team collaboration via Model Context Protocol.
    11
    231 npm
    2
    MIT

  • Reverie

    seabearDEV
    A
    license
    Not graded
    quality
    A
    maintenance
    CLI + MCP server that bootstraps persistent project context for any AI agent, storing structured information using hierarchical dot notation and exposing it via MCP tools for session-over-session knowledge growth.
    1
    MIT

  • PCP

    IsoCodeCrafter
    A
    license
    Not graded
    quality
    B
    maintenance
    Standardize Context, Not Intelligence. An open protocol and native MCP server for preserving, organizing, and serving structured project context (architecture, decision logs, domain rules, and roadmap) to AI coding assistants (Cursor, Claude Desktop, Antigravity) with built-in CLI verification
    MIT

  • rust-faf-mcp RMCP

    Wolfe-Jam
    A
    license
    Not graded
    quality
    A
    maintenance
    Persistent project context in Rust. 8 MCP tools via rmcp SDK — parse, validate, score, compress, discover, and token analysis. Single binary, zero config. IANA-registered format (application/vnd.faf+yaml). One file, every AI platform.
    252 npm
    4
    MIT

  • promem-mcp

    DIP-RO
    A
    license
    B
    quality
    A
    maintenance
    Enables AI coding agents to maintain persistent project context, including rules, decisions, environment intelligence, and Git history, using a local-first MCP server with automatic project detection and token-efficient retrieval.
    13
    MIT
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 15 tools

Disambiguation3/5

Several tools overlap in function: faf_score, faf_check, faf_doctor, and faf_trust all inspect the .faf and report status, so an agent could misselect among them. Worse, faf_claude (with format flags/all) writes AGENTS.md, .cursorrules, and GEMINI.md — duplicating the write direction of faf_agents, faf_cursor, and faf_gemini. The detailed cross-referencing descriptions mitigate this, but the boundaries are genuinely fuzzy.

Naming Consistency4/5

Every tool uses a consistent faf_ snake_case prefix, which is highly predictable. The suffixes mix verbs (init, score, check, sync) with target-resource nouns (claude, cursor, gemini, agents, git), a minor stylistic deviation but still readable and coherent.

Tool Count4/5

15 tools is within the reasonable upper range for a multi-format context manager. However, the four platform-specific tools (claude, cursor, gemini, agents) are near-duplicates of one parameterized operation, suggesting the set is slightly heavier than necessary.

Completeness4/5

Coverage spans creation (init, auto, git), evaluation (score, check, doctor, trust), updating (sync, go), and import/export across AI formats, which is solid lifecycle coverage. The gap is that faf_context's description references faf_read and faf_write tools that are absent from the surface, leaving no direct raw read/write operation.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources