Skip to main content

MCP server for Symbols.app — documentation search and framework reference

Project description

symbols-mcp

mcp-name: io.github.symbo-ls/symbols-mcp

MCP server for Symbols.app — provides documentation search and framework reference tools for AI coding assistants (Cursor, Claude Code, Windsurf, etc.).

No API keys required. All tools work fully offline using bundled documentation.


Tools

  • get_project_rules — Returns mandatory Symbols.app rules. Call this before any code generation task.
  • search_symbols_docs — Keyword search across all bundled Symbols documentation files.

Resources

  • symbols://skills/domql-v3-reference — Complete DOMQL v3 syntax reference
  • symbols://skills/project-structure — Project folder structure and file conventions
  • symbols://skills/design-direction — UI/UX design direction
  • symbols://skills/migration-guide — React/Angular/Vue → Symbols migration guide
  • symbols://skills/v2-to-v3-migration — DOMQL v2 → v3 changes
  • symbols://skills/ssr-brender — Server-side rendering with brender (SSR/SSG)
  • symbols://skills/quickstart — CLI quickstart
  • symbols://reference/spacing-tokens — Spacing token reference
  • symbols://reference/atom-components — Built-in atom components
  • symbols://reference/event-handlers — Event handler reference

Prompts

  • symbols_component_prompt — Template for generating a component
  • symbols_migration_prompt — Template for migrating framework code
  • symbols_project_prompt — Template for scaffolding a full project
  • symbols_review_prompt — Template for reviewing Symbols code

Installation

pip install symbols-mcp

Or with uv:

uvx symbols-mcp

Configuration

Add to your MCP client config (e.g. mcp.json):

{
  "mcpServers": {
    "symbols": {
      "command": "uvx",
      "args": ["symbols-mcp"]
    }
  }
}

Custom skills directory

To point at a different skills folder:

{
  "mcpServers": {
    "symbols": {
      "command": "uvx",
      "args": ["symbols-mcp"],
      "env": {
        "SYMBOLS_SKILLS_DIR": "/path/to/your/skills"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

symbols_mcp-1.0.13.tar.gz (145.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

symbols_mcp-1.0.13-py3-none-any.whl (110.8 kB view details)

Uploaded Python 3

File details

Details for the file symbols_mcp-1.0.13.tar.gz.

File metadata

  • Download URL: symbols_mcp-1.0.13.tar.gz
  • Upload date:
  • Size: 145.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.3 {"installer":{"name":"uv","version":"0.10.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for symbols_mcp-1.0.13.tar.gz
Algorithm Hash digest
SHA256 71f64a5a0712dfcd478c15203d17be40ec68cabe91b12e83d8904af0c981788c
MD5 0e05e841abb28fe97d23a92e385d96cd
BLAKE2b-256 3ed69bc596c853c349929685c20811a81e4a0fb3d2fb700bf381a2ecefec1979

See more details on using hashes here.

File details

Details for the file symbols_mcp-1.0.13-py3-none-any.whl.

File metadata

  • Download URL: symbols_mcp-1.0.13-py3-none-any.whl
  • Upload date:
  • Size: 110.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.3 {"installer":{"name":"uv","version":"0.10.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for symbols_mcp-1.0.13-py3-none-any.whl
Algorithm Hash digest
SHA256 0c83a1ac117c69f67dc730c9eabcd97a6ab231255be8d37e77e1a186411b9e06
MD5 540c2db4b3db77f0070de31aef19e549
BLAKE2b-256 f12e268084e0677aae60606071e60091bdb726a26e711c9514eb315314dabc3e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page