Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
MCP servers/Search & Web Crawling
sammysnake-d avatar

Fast Context

sammysnake-d/fast-context-mcp

Wraps Windsurf's reverse-engineered SWE-grep protocol to bring AI-powered semantic code search to any MCP client. Instead of exact string matching, you ask natural language questions like "where's the authentication logic?" and get back specific file paths with line ranges. Under the hood, it sends your project's directory tree to Windsurf's Devstral model, which generates ripgrep commands, executes them locally, and iterates until it finds relevant code sections. Bundles ripgrep via npm so no system dependencies needed. Requires a Windsurf API key but works with their free tier.

GitHub stars
173
last updated
Feb 9, 2026
View on GitHubSave

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Readme

Fast Context MCP

npm version node version license MCPVault: claimed

AI-driven semantic code search as an MCP tool — powered by Windsurf's reverse-engineered SWE-grep protocol.

Any MCP-compatible client (Claude Code, Claude Desktop, Cursor, etc.) can use this to search codebases with natural language queries. All tools are bundled via npm — no system-level dependencies needed (ripgrep via @vscode/ripgrep, tree via tree-node-cli). Works on macOS, Windows, and Linux.

How It Works

You: "where is the authentication logic?"
         │
         ▼
┌─────────────────────────┐
│  Fast Context MCP       │
│  (local MCP server)     │
│                         │
│  1. Maps project → /codebase
│  2. Sends query to Windsurf Devstral API
│  3. AI generates rg/readfile/tree commands
│  4. Executes commands locally (built-in rg)
│  5. Returns results to AI
│  6. Repeats for N rounds
│  7. Returns file paths + line ranges
│     + suggested search keywords
└─────────────────────────┘
         │
         ▼
Found 3 relevant files.
  [1/3] /project/src/auth/handler.py (L10-60)
  [2/3] /project/src/middleware/jwt.py (L1-40)
  [3/3] /project/src/models/user.py (L20-80)

Suggested search keywords:
  authenticate, jwt.*verify, session.*token

Prerequisites

  • Node.js >= 18
  • Windsurf account — free tier works (needed for API key)

No need to install ripgrep — it's bundled via @vscode/ripgrep.

Installation

Option 1: npm (Recommended)

# Latest stable release
npm install @sammysnake/fast-context-mcp

# Or beta/next release
npm install @sammysnake/fast-context-mcp@next

Option 2: From Source

git clone https://github.com/SammySnake-d/fast-context-mcp.git
cd fast-context-mcp
npm install

Setup

1. Get Your Windsurf/Devin API Key

The server auto-extracts the API key from Devin CLI/Desktop or a legacy Windsurf installation. You can also use the extract_windsurf_key MCP tool after setup, or set WINDSURF_API_KEY manually.

Desktop credentials are discovered in this order: Devin, legacy Deviv, then Windsurf.

PlatformPath
macOS~/Library/Application Support/Devin/User/globalStorage/state.vscdb
Windows%APPDATA%/Devin/User/globalStorage/state.vscdb
Linux~/.config/Devin/User/globalStorage/state.vscdb

On WSL/Linux, the server first checks Devin CLI credentials at ~/.local/share/devin/credentials.toml. If a Windows-extracted key returns 403 inside WSL, run devin login inside WSL and retry.

2. Configure MCP Client

Claude Code

Add to ~/.claude.json under mcpServers:

{
  "fast-context": {
    "command": "npx",
    "args": ["-y", "--prefer-online", "@sammysnake/fast-context-mcp"],
    "env": {
      "WINDSURF_API_KEY": "sk-ws-01-xxxxx"
    }
  }
}

For beta/next release:

{
  "fast-context": {
    "command": "npx",
    "args": ["-y", "--prefer-online", "@sammysnake/fast-context-mcp@next"],
    "env": {
      "WINDSURF_API_KEY": "sk-ws-01-xxxxx"
    }
  }
}
Claude Desktop

Add to claude_desktop_config.json under mcpServers:

{
  "fast-context": {
    "command": "npx",
    "args": ["-y", "--prefer-online", "@sammysnake/fast-context-mcp"],
    "env": {
      "WINDSURF_API_KEY": "sk-ws-01-xxxxx"
    }
  }
}

For beta/next release:

{
  "fast-context": {
    "command": "npx",
    "args": ["-y", "--prefer-online", "@sammysnake/fast-context-mcp@next"],
    "env": {
      "WINDSURF_API_KEY": "sk-ws-01-xxxxx"
    }
  }
}

If WINDSURF_API_KEY is omitted, the server auto-discovers it from your local Windsurf installation.

Environment Variables

VariableDefaultDescription
WINDSURF_API_KEY(auto-discover)Windsurf API key
FC_MAX_TURNS3Search rounds per query (more = deeper but slower)
FC_MAX_COMMANDS8Max parallel commands per round
FC_TIMEOUT_MS30000Connect-Timeout-Ms for streaming requests
FC_HIDE_EXTRACT_WINDSURF_KEY_TOOLfalseHide extract_windsurf_key from MCP tools when set to 1, true, yes, or on
FC_RESULT_MAX_LINES50Max lines per command output (truncation)
FC_LINE_MAX_CHARS250Max characters per output line (truncation)
FC_CACHE_DISABLED(unset)Disable the in-memory result cache with 1, true, yes, or on
FC_CACHE_TTL_MS300000Result-cache TTL; <=0 disables caching
FC_CACHE_MAX_ENTRIES200Maximum in-memory cache entries
FC_ALLOW_INSECURE_TLS(unset)Set to 1 only when a trusted corporate proxy requires disabled TLS verification
WS_MODELMODEL_SWE_1_6_FASTWindsurf model name
WS_APP_VER1.48.2Windsurf app version (protocol metadata)
WS_LS_VER1.9544.35Windsurf language server version (protocol metadata)

Available Models

The model can be changed by setting WS_MODEL (see environment variables above).

Available Models

Default: MODEL_SWE_1_6_FAST — fastest speed, richest grep keywords, finest location granularity.

MCP Tools

fast_context_search

AI-driven semantic code search with tunable parameters.

ParameterTypeRequiredDefaultDescription
querystringYes—Natural language search query
project_pathstringNocwdAbsolute path to project root
tree_depthintegerNo3Directory tree depth for repo map (1-6). Higher = more context but larger payload. Auto falls back to lower depth if tree exceeds 250KB. Use 1-2 for huge monorepos (>5000 files), 3 for most projects, 4-6 for small projects.
max_turnsintegerNo3Search rounds (1-5). More = deeper search but slower. Use 1-2 for simple lookups, 3 for most queries, 4-5 for complex analysis.
max_resultsintegerNo10Maximum number of files to return (1-30). Smaller = more focused, larger = broader exploration.
exclude_pathsstring[]No[]Directory/file patterns excluded from the repository map and search context.

Returns:

  1. Relevant files with line ranges
  2. Suggested search keywords (rg patterns used during AI search)
  3. Diagnostic metadata ([config] line showing actual tree_depth used, tree size, and whether fallback occurred)

Example output:

Found 3 relevant files.

  [1/3] /project/src/auth/handler.py (L10-60, L120-180)
  [2/3] /project/src/middleware/jwt.py (L1-40)
  [3/3] /project/src/models/user.py (L20-80)

grep keywords: authenticate, jwt.*verify, session.*token

[config] tree_depth=3, tree_size=12.5KB, max_turns=3

Error output includes status-specific hints:

Error: Request failed: HTTP 403

[hint] 403 Forbidden: Authentication failed. The API key may be expired or revoked.
Try re-extracting with extract_windsurf_key, or set a fresh WINDSURF_API_KEY env var.
If you are running inside WSL, run `devin login` inside WSL so `~/.local/share/devin/credentials.toml` exists.
Error: Request failed: HTTP 413

[diagnostic] tree_depth_used=3, tree_size=280.0KB (auto fell back from requested depth)
[hint] If the error is payload-related, try a lower tree_depth value.

extract_windsurf_key

Extract Windsurf API Key from local installation. No parameters.

Set FC_HIDE_EXTRACT_WINDSURF_KEY_TOOL=1 at MCP server startup to hide this tool from tools/list. This does not disable internal API-key auto-discovery for fast_context_search.

Project Structure

fast-context-mcp/
├── package.json
├── src/
│   ├── server.mjs        # MCP server entry point
│   ├── core.mjs          # Auth, message building, streaming, search loop
│   ├── executor.mjs      # Tool executor: rg, readfile, tree, ls, glob
│   ├── extract-key.mjs   # Windsurf API Key extraction (SQLite)
│   ├── path-safety.mjs   # Project-root confinement for model-selected paths
│   ├── response-repair.mjs # Malformed response repair and evidence salvage
│   ├── shared.mjs        # Repository map, answer parser, prompt builder
│   ├── cache.mjs         # In-memory search-result cache
│   └── protobuf.mjs      # Protobuf encoder/decoder + Connect-RPC frames
├── test/                 # Unit and MCP stdio integration tests
├── README.md
└── LICENSE

How the Search Works

  1. Project directory is mapped to virtual /codebase path
  2. Directory tree generated at requested depth (default L=3), with automatic fallback to lower depth if tree exceeds 250KB
  3. Query + directory tree sent to Windsurf's Devstral model via Connect-RPC/Protobuf
  4. Devstral generates tool commands (ripgrep, file reads, tree, ls, glob)
  5. Commands executed locally in parallel (up to FC_MAX_COMMANDS per round)
  6. Results sent back to Devstral for the next round
  7. After max_turns rounds, Devstral returns file paths + line ranges
  8. All rg patterns used during search are collected as suggested keywords
  9. Diagnostic metadata appended to help the calling AI tune parameters

Technical Details

  • Protocol: Connect-RPC over HTTP/1.1, Protobuf encoding, gzip compression
  • Model: Devstral (MODEL_SWE_1_6_FAST, configurable)
  • Local tools: rg (bundled via @vscode/ripgrep), readfile (Node.js fs), tree (tree-node-cli), ls (Node.js fs), glob (Node.js fs)
  • Auth: API Key → JWT (auto-fetched per session)
  • Runtime: Node.js >= 18 (ESM)

Dependencies

PackagePurpose
@modelcontextprotocol/sdkMCP server framework
@vscode/ripgrepBundled ripgrep binary (cross-platform)
tree-node-cliCross-platform directory tree (replaces system tree)
sql.jsRead Devin/Windsurf's local SQLite DB without a native build step
zod (^3.25.76)Schema validation; avoids the incomplete 3.25.0 tarball served by some npm mirrors

友情链接

  • LINUX DO

License

MIT

Details

Repository
github.com/sammysnake-d/fast-context-mcp
Category
Search & Web Crawling

Related Search & Web Crawling MCP servers

View all
1netboxlabs avatarNetBoxnetboxlabs/netbox-mcp-serverQueries core NetBox data via MCP tools to fetch objects, details, and changelogs for LLM-assisted workflows.172stars
2mariadb avatarMCP MariaDB Servermariadb/mcpProvides an MCP interface to manage and query MariaDB databases with SQL and vector/embedding search.168stars
334892002 avatarBilibili34892002/bilibili-mcp-jsProvides Bilibili video search, popular lists, video details, creator info, and番剧 schedules via MCP167stars
4sathergate avatarSearchcraftsathergate/sathergate-toolkitFull-text search for Next.js. BM25 scoring and fuzzy matching, no external service.0stars
5petabridge avatarMemorizerpetabridge/memorizer-v1Provides a memory store with vector search, versioning, and MCP integration for AI agents.164stars
6elara-labs avatarCode Context Engineelara-labs/code-context-engineIndex your codebase. AI searches instead of re-reading files. 94% token savings.160stars