Dolphin MCP

🚀 dolphin-mcp

This is an MCP server for Dolphin semantic code search, conforming to the MCP spec. It simplifies the process of semantic code search and provides useful features for code retrieval and management.

🚀 Quick Start

No installation is needed. You can use bunx directly:

bunx dolphin-mcp

✨ Features

• Semantically query code and docs across indexed repositories.
• Fetch code chunks and file slices with citations.
• Report vector store information.
• Generate vscode://file URIs for code opening in the editor.

📦 Installation

Optional Global Installation

If you prefer installing globally:

bun install -g dolphin-mcp

Then use dolphin-mcp instead of bunx dolphin-mcp.

📚 Documentation

Configuration

Continue.dev

Add the following to config.yaml:

mcpServers:
  - name: Dolphin-KB
    command: bunx
    args:
      - dolphin-mcp
    env:
      DOLPHIN_API_URL: "http://127.0.0.1:7777"
      # Optional: Performance optimization for parallel snippet fetching
      MAX_CONCURRENT_SNIPPET_FETCH: "8"
      SNIPPET_FETCH_TIMEOUT_MS: "2000"
      SNIPPET_FETCH_RETRY_ATTEMPTS: "1"

Claude Desktop

Add the following to claude_desktop_config.json:

{
  "mcpServers": {
    "dolphin-kb": {
      "command": "bunx",
      "args": ["dolphin-mcp"],
      "env": {
        "DOLPHIN_API_URL": "http://127.0.0.1:7777",
        "MAX_CONCURRENT_SNIPPET_FETCH": "8",
        "SNIPPET_FETCH_TIMEOUT_MS": "2000",
        "SNIPPET_FETCH_RETRY_ATTEMPTS": "1"
      }
    }
  }
}

Environment Variables

Parallel Snippet Fetching Configuration

These variables control the performance optimization for parallel snippet fetching in search_knowledge:

Configuration Presets

Conservative (recommended for limited resources):

MAX_CONCURRENT_SNIPPET_FETCH=4
SNIPPET_FETCH_TIMEOUT_MS=1500
SNIPPET_FETCH_RETRY_ATTEMPTS=1

Recommended (balanced performance):

MAX_CONCURRENT_SNIPPET_FETCH=8
SNIPPET_FETCH_TIMEOUT_MS=2000
SNIPPET_FETCH_RETRY_ATTEMPTS=1

Performance (maximum throughput):

MAX_CONCURRENT_SNIPPET_FETCH=10
SNIPPET_FETCH_TIMEOUT_MS=3000
SNIPPET_FETCH_RETRY_ATTEMPTS=2

Available Tools

💻 Basic Usage

search_knowledge

Semantically query code and docs across indexed repositories and return ranked snippets with citations.

{
  "query": "string (required)",
  "repos": ["string"],
  "path_prefix": ["string"],
  "exclude_paths": ["string"],
  "exclude_patterns": ["string"],
  "top_k": "number (1 - 100)",
  "max_snippets": "number",
  "embed_model": "small | large",
  "score_cutoff": "number"
}

Filtering Options:

• repos: Include only specific repositories.
• path_prefix: Include only paths matching these prefixes (e.g., ["src/", "lib/"]).
• exclude_paths: Exclude paths matching these prefixes (e.g., ["tests/", "node_modules/", "dist/"]).
• exclude_patterns: Exclude files matching glob patterns (e.g., ["*.test.ts", "*.config.json"]).

Example:

{
  "query": "authentication logic",
  "repos": ["myapp"],
  "path_prefix": ["src/"],
  "exclude_paths": ["tests/"],
  "exclude_patterns": ["*.spec.ts", "*.mock.ts"]
}

fetch_chunk

Fetch a chunk by chunk_id and return fenced code with citation.

{
  "chunk_id": "string (required)"
}

fetch_lines

Fetch a file slice [start, end] inclusive from disk and return fenced code with citation.

{
  "repo": "string (required)",
  "path": "string (required)",
  "start": "number (required, 1 - indexed)",
  "end": "number (required, inclusive)"
}

get_vector_store_info

Report namespaces, dims, limits, and approximate counts.

{}

open_in_editor

Compute a vscode://file URI for a repo path and optional position.

{
  "repo": "string (required)",
  "path": "string (required)",
  "line": "number (1 - indexed)",
  "column": "number (1 - indexed)"
}

🔧 Technical Details

Requirements

• Bun >= 1.0.0 - Install
• Dolphin API running on the configured endpoint

📄 License

This project is licensed under the MIT license. See the LICENSE file for details.

🔗 Links

• NPM Package
• GitHub Repository
• MCP Specification