About symbols
Symbols MCP connects to language servers to help coding agents read, inspect, and navigate code symbols. Its compact set of tools, resources, and skills covers symbol search, references, call relationships, and diagnostics.
Key features
- 01Create file symbol outlines
- 02Inspect symbol docs and implementation locations
- 03Search symbols across a codebase
- 04Find references and call relationships
- 05Rename symbols and retrieve diagnostics
- 06View language server status and logs
Use cases
- 01Explore a codebase and its dependencies
- 02Locate symbol declarations and implementations
- 03Trace call relationships and references
- 04Troubleshoot language server setup and logs
MCP support
The MCP server connects to selected language servers and exposes code-symbol tools, language-server profile resources, and related skills to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESymbols MCP
Read, inspect and navigate through codebase symbols by connecting to Language Servers.
Introduction
By connecting to a Language Server of choice this MCP server makes it easy and efficient for coding agents to explore and navigate the codebase and its dependencies. The server offers a minimal set of tools, resources and skills intended to be simple to use and light on the model's context.
Tools
outline: returns an outline of code symbols in a file, optionally with a small code snippetinspect: returns docs, declaration and implementation locations for a symbol, including third-party onessearch: returns matching symbols across the codebasereferences: finds all references of a symbol across the codebasecall_hierarchy: returns incoming and outgoing call relationships for a callable symbolrename: renames all references of a symbol across the codebasediagnostics: returns active diagnostics in a given filecompletion: returns contextual completions at a given locationreload: reloads the effective config and reapplies it to currently running language servers
Resources
language-servers://profiles: returns the configured language servers along with their state.language-servers://profiles/{name}: returns a more detailed view of one language server.language-servers://profiles/{name}/logs: returns the Language Server logs for troubleshooting.
Skills
install-language-server: installs, configures, validates, or troubleshoots a language-server profile for the current workspace.language-server-navigation: guides symbol inspection, references, rename, diagnostics, and search through Language Server tools before falling back to text search.
Installation
Codex
codex plugin marketplace add p1va/symbols
codex plugin add symbols@symbols
Then ask Codex:
Please install and configure the language servers relevant to this codebase
Antigravity
agy plugin install https://github.com/p1va/symbols.git
Then ask Antigravity:
Install and configure the language servers relevant to this codebase.
Manual Installation
For manual configuration and language servers examples see here.
Development
pnpm lintoutputs the lint violationspnpm lint:fixattempts to fix lint violationspnpm formatformats the codebasepnpm format:checkchecks formatting without changing filespnpm devstarts in development modepnpm buildruns the linter and buildpnpm startstarts the built artifactspnpm test:unitruns the unit testspnpm test:integration:{language id}runs the integration tests for a given language
Release
pnpm version patchto synchronize generated assets, bump the version, and create a single commit and tag. Useminorormajorwhen appropriate.git push --follow-tagsto push the commit and tag.
The version lifecycle checks formatting, mirrors .agents/skills/ into the
Antigravity and Codex distributions, and updates the versioned Codex plugin
manifest before the commit and tag are created.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.