Fast Context MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fast Context MCP find where the authentication logic is defined"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fast Context MCP
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.*tokenRelated MCP server: codesteer-atlas
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
git clone https://github.com/SammySnake-d/fast-context-mcp.git
cd fast-context-mcp
npm installSetup
1. Get Your Windsurf API Key
The server auto-extracts the API key from your local Windsurf installation. You can also use the extract_windsurf_key MCP tool after setup, or set WINDSURF_API_KEY manually.
Key is stored in Windsurf's local SQLite database:
Platform | Path |
macOS |
|
Windows |
|
Linux |
|
2. Configure MCP Client
Claude Code
Add to ~/.claude.json under mcpServers:
{
"fast-context": {
"command": "node",
"args": ["/absolute/path/to/fast-context-mcp/src/server.mjs"],
"env": {
"WINDSURF_API_KEY": "sk-ws-01-xxxxx"
}
}
}Claude Desktop
Add to claude_desktop_config.json under mcpServers:
{
"fast-context": {
"command": "node",
"args": ["/absolute/path/to/fast-context-mcp/src/server.mjs"],
"env": {
"WINDSURF_API_KEY": "sk-ws-01-xxxxx"
}
}
}If
WINDSURF_API_KEYis omitted, the server auto-discovers it from your local Windsurf installation.
Environment Variables
Variable | Default | Description |
| (auto-discover) | Windsurf API key |
|
| Search rounds per query (more = deeper but slower) |
|
| Max parallel commands per round |
|
| Connect-Timeout-Ms for streaming requests |
|
| Max lines per command output (truncation) |
|
| Max characters per output line (truncation) |
|
| Windsurf model name |
|
| Windsurf app version (protocol metadata) |
|
| Windsurf language server version (protocol metadata) |
Available Models
The model can be changed by setting WS_MODEL (see environment variables above).

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.
Parameter | Type | Required | Default | Description |
| string | Yes | — | Natural language search query |
| string | No | cwd | Absolute path to project root |
| integer | No |
| Directory 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. |
| integer | No |
| Search rounds (1-5). More = deeper search but slower. Use 1-2 for simple lookups, 3 for most queries, 4-5 for complex analysis. |
| integer | No |
| Maximum number of files to return (1-30). Smaller = more focused, larger = broader exploration. |
Returns:
Relevant files with line ranges
Suggested search keywords (rg patterns used during AI search)
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=3Error 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.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.
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)
│ └── protobuf.mjs # Protobuf encoder/decoder + Connect-RPC frames
├── README.md
└── LICENSEHow the Search Works
Project directory is mapped to virtual
/codebasepathDirectory tree generated at requested depth (default L=3), with automatic fallback to lower depth if tree exceeds 250KB
Query + directory tree sent to Windsurf's Devstral model via Connect-RPC/Protobuf
Devstral generates tool commands (ripgrep, file reads, tree, ls, glob)
Commands executed locally in parallel (up to
FC_MAX_COMMANDSper round)Results sent back to Devstral for the next round
After
max_turnsrounds, Devstral returns file paths + line rangesAll rg patterns used during search are collected as suggested keywords
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
Package | Purpose |
| MCP server framework |
| Bundled ripgrep binary (cross-platform) |
| Cross-platform directory tree (replaces system |
| Read Windsurf's local SQLite DB |
| Schema validation (MCP SDK requirement) |
License
MIT
Available Tools
2 toolsextract_windsurf_keyA
Extract Windsurf API Key from local installation. Auto-detects OS (macOS/Windows/Linux) and reads the API key from Windsurf's local database. Set the result as WINDSURF_API_KEY env var.
Inputs: no named parameters.
fast_context_searchA
AI-driven semantic code search using Windsurf's Devstral model. Searches a codebase with natural language and returns relevant file paths with line ranges, plus suggested grep keywords for follow-up searches. Parameter tuning guide:
tree_depth: Controls how much directory structure the remote AI sees before searching. If you get a payload/size error, REDUCE this value. If search results are too shallow (missing files in deep subdirectories), INCREASE this value.
max_turns: Controls how many search-execute-feedback rounds the remote AI gets. If results are incomplete or the AI didn't find enough files, INCREASE this value. If you want a quick rough answer, use 1. Response includes a [config] line showing actual parameters used — use this to decide adjustments on retry.
Inputs: query (required), max_turns, tree_depth, max_results, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools serve completely distinct purposes: one performs AI-powered code search, and the other extracts an API key. There is no overlap or ambiguity between them.
Both tools use snake_case and follow a descriptive noun-verb pattern (fast_context_search, extract_windsurf_key). The naming is mostly consistent, though one is more of an adjective_noun_verb while the other is a clear verb_noun.
With only two tools, the server feels thin for its purpose. However, it is narrowly focused on AI-driven search, and each tool is substantial, so the count is borderline acceptable.
The core search workflow is covered by the search tool, which includes configurable parameters for depth and turns. The key extraction is a necessary setup step. There are no obvious dead ends, though a few extra utilities (e.g., search history or config management) could enhance completeness.
Maintenance
Related MCP Connectors
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
An MCP server that gives your AI access to the source code and docs of all public github repos
Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI-driven semantic code search by leveraging Windsurf's reverse-engineered protocol to perform multi-round local searches using natural language. It automatically executes bundled ripgrep and file operations to return relevant code snippets and file paths to MCP-compatible clients.299 npm365MIT
- AlicenseAqualityBmaintenanceLocal MCP server for semantic code search using Tree-sitter AST parsing, local embeddings, and hybrid search; enables indexing and querying codebases entirely offline.7MIT
- AlicenseAqualityDmaintenanceLocal-first MCP server for semantic + keyword hybrid code search. Zero external services, no API keys required.2MIT
- AlicenseNot gradedqualityDmaintenanceSemantic + lexical code search as an MCP server. Agents query in natural language and get back ranked file:line ranges to read precisely.11 npm1MIT