Fast Context MCP is an AI-powered semantic code search tool for MCP clients (Claude Code, Claude Desktop, Cursor, etc.) powered by Windsurf's Devstral model.
Core capabilities:
Semantic code search (fast_context_search): Query codebases using natural language (e.g., "where is the authentication logic?") to receive relevant file paths with line ranges, suggested grep/regex keywords, and diagnostic metadata — no exact keywords needed
Extract Windsurf API key (extract_windsurf_key): Automatically locate and extract the Windsurf API key from local SQLite databases on macOS, Windows, or Linux
Key features:
Tunable search parameters: directory tree depth (tree_depth), AI search rounds (max_turns), and result limits (max_results)
Cross-platform with no system-level dependencies (ripgrep and tree are bundled)
All search commands execute locally for privacy and speed
Configurable via environment variables (API key, model, turn limits)
Click on "Install 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 where is the authentication and session logic located?"
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.
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.
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: code-rag
Node.js >= 18
Windsurf account — free tier works (needed for API key)
No need to install ripgrep — it's bundled via @vscode/ripgrep.
# Latest stable release
npm install @sammysnake/fast-context-mcp
# Or beta/next release
npm install @sammysnake/fast-context-mcp@nextgit clone https://github.com/SammySnake-d/fast-context-mcp.git
cd fast-context-mcp
npm installThe 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.
Platform | Path |
macOS |
|
Windows |
|
Linux |
|
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.
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"
}
}
}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_KEYis omitted, the server auto-discovers it from your local Windsurf installation.
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 |
|
| Hide |
|
| Max lines per command output (truncation) |
|
| Max characters per output line (truncation) |
| (unset) | Disable the in-memory result cache with |
|
| Result-cache TTL; |
|
| Maximum in-memory cache entries |
| (unset) | Set to |
|
| Windsurf model name |
|
| Windsurf app version (protocol metadata) |
|
| Windsurf language server version (protocol metadata) |
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.
fast_context_searchAI-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. |
| string[] | No |
| Directory/file patterns excluded from the repository map and search context. |
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.
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_keyExtract 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.
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
└── LICENSEProject directory is mapped to virtual /codebase path
Directory 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_COMMANDS per round)
Results sent back to Devstral for the next round
After max_turns rounds, Devstral returns file paths + line ranges
All rg patterns used during search are collected as suggested keywords
Diagnostic metadata appended to help the calling AI tune parameters
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)
Package | Purpose |
| MCP server framework |
| Bundled ripgrep binary (cross-platform) |
| Cross-platform directory tree (replaces system |
| Read Devin/Windsurf's local SQLite DB without a native build step |
| Schema validation; avoids the incomplete |
MIT
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.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description fully covers the tool's behavior: auto-detecting OS, reading a local database, and setting an environment variable. It could mention potential permissions or security considerations for reading a local database, but overall is transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two clear, front-loaded sentences. No unnecessary information, every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and a straightforward operation, the description provides complete context: what the tool does, how it works (auto-detection), and the outcome (setting env var).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and 100% schema coverage, so the baseline is 4. The description does not need to add parameter information, and it adequately explains that no parameters are needed due to auto-detection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: extracting the Windsurf API key from the local installation, with OS auto-detection and env var setting. It distinguishes from the sibling tool 'fast_context_search' which serves a different function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the outcome (setting the env var) but does not provide explicit guidance on when or when not to use this tool versus alternatives. Usage context is implied but not detailed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language search query (e.g. "where is auth handled", "database connection pool") | |
| project_path | No | Absolute path to project root. Empty = current working directory. | |
| tree_depth | No | Directory tree depth for the initial repo map sent to the remote AI. Default 3. Use 1-2 for huge monorepos (>5000 files) or if you get payload size errors. Use 4-6 for small projects (<200 files) where you want the AI to see deeper structure. Auto falls back to a lower depth if tree output exceeds 250KB. | |
| max_turns | No | Number of search rounds. Each round: remote AI generates search commands → local execution → results sent back. Default 3. Use 1 for quick simple lookups. Use 4-5 for complex queries requiring deep tracing across many files. More rounds = better results but slower and uses more API quota. | |
| max_results | No | Maximum number of files to return. Default 10. Use a smaller value (3-5) for focused queries. Use a larger value (15-30) for broad exploration queries. | |
| exclude_paths | No | Directory/file patterns to exclude from tree and search context. Useful for reducing payload size on large repos. Examples: ['node_modules', 'dist', '.git', 'build', 'coverage', '*.min.*'] |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully explains the search process: rounds of search-execute-feedback, auto fallback for tree depth if payload exceeds 250KB, and mentions API quota usage for more rounds. This provides comprehensive behavioral insight.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a main overview and a parameter tuning guide. It is concise overall but the tuning guide could be slightly more compact. Still, it is clear and front-loaded with key purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 6 parameters, 100% schema coverage, no output schema, and only one sibling, the description covers purpose, behavior, tuning, and response content (including [config] line). It provides sufficient context for an agent to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds valuable tuning context for tree_depth and max_turns beyond the schema, explaining payload/size errors and result completeness. For other parameters, the schema already suffices. Thus, a 4 is warranted.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs AI-driven semantic code search, returns file paths with line ranges and grep keywords. It distinguishes itself from the only sibling, extract_windsurf_key, which extracts a key.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes a parameter tuning guide that explains when to adjust tree_depth and max_turns based on errors or shallow results. It also advises using the [config] line in responses for retry decisions. However, it does not explicitly state when not to use this tool, but given only one dissimilar sibling, this is acceptable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.2.1fast_context_search4 fields changedInput schema / properties / exclude_pathsAdded value: +{
+ "default": [],
+ "description": "Directory/file patterns to exclude from tree and search context. Useful for reducing payload size on large repos. Examples: ['node_modules', 'dist', '.git', 'build', 'coverage', '*.min.*']",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+}Input schema / properties / max_resultsAdded value: +{
+ "default": 10,
+ "description": "Maximum number of files to return. Default 10. Use a smaller value (3-5) for focused queries. Use a larger value (15-30) for broad exploration queries.",
+ "maximum": 30,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / max_turnsAdded value: +{
+ "default": 3,
+ "description": "Number of search rounds. Each round: remote AI generates search commands → local execution → results sent back. Default 3. Use 1 for quick simple lookups. Use 4-5 for complex queries requiring deep tracing across many files. More rounds = better results but slower and uses more API quota.",
+ "maximum": 5,
+ "minimum": 1,
+ "type": "integer"
+}Input schema / properties / tree_depthAdded value: +{
+ "default": 3,
+ "description": "Directory tree depth for the initial repo map sent to the remote AI. Default 3. Use 1-2 for huge monorepos (>5000 files) or if you get payload size errors. Use 4-6 for small projects (<200 files) where you want the AI to see deeper structure. Auto falls back to a lower depth if tree output exceeds 250KB.",
+ "maximum": 6,
+ "minimum": 1,
+ "type": "integer"
+}v1.0.0extract_windsurf_keyfast_context_searchThe two tools have completely distinct purposes: one extracts an API key from a local installation, the other performs semantic code search. No overlap or ambiguity exists.
Both tools use snake_case and follow a descriptive pattern (extract_* and fast_*). Although the verb style differs slightly (command vs. brand adjective), the naming is clear and consistent in format.
With only two tools, the server feels minimal. While the tools are focused, the count is on the low end of what is typically expected, making it borderline appropriate.
The server covers API key extraction and semantic search, but lacks related operations like API key management, file content retrieval, or result navigation. Significant gaps exist for a context-focused server.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
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
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SammySnake-d/fast-context-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
