mcp-language-server
An MCP (Model Context Protocol) server that acts as a unified frontend for multiple Language Server Protocol (LSP) servers. It routes MCP tool requests to the appropriate underlying language server based on file extension or an explicit language argument, and supports operations like definition lookup, references, diagnostics, code lenses, executing code lens actions, and applying text edits (optionally with bracket-preservation safeguards).
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Security details are not documented in the README. The server is intended to run as a local MCP process communicating over stdio, so TLS is not directly applicable, but transport safety depends on the MCP client deployment. Authentication/authorization and access controls are not mentioned; if exposed beyond localhost/trusted clients, it could allow an agent to trigger LSP operations and apply workspace edits. The README references a dependency (`mcp-golang`) and includes attribution for code adapted from gopls protocol internals; no dependency audit or CVE status is provided here.
⚡ Reliability
Best When
Used locally (or in a trusted environment) with a known MCP client (e.g., Claude Desktop) and with LSP servers installed for the target languages, where the agent needs code intelligence and safe edit application.
Avoid When
Avoid when you cannot trust the agent/user inputs that determine which file/language to operate on, or when the server will be reachable by untrusted network clients; also avoid when you need guaranteed idempotency or transaction-like edit safety beyond the described bracket-preservation option.
Use Cases
- • Provide LLMs/agents with accurate code understanding across multiple languages via one MCP server
- • Definition and reference lookups for mixed-language workspaces
- • Diagnostics and code lens assistance in an agent workflow
- • Automated refactoring/editing workflows where edits need to be applied back to the workspace
- • IDE-like assistance for symbol-level navigation and targeted code modifications
Not For
- • Remote multi-tenant SaaS use without additional security controls
- • Public exposure of the server to untrusted users/requests (it can drive local LSP servers and apply edits)
- • Use as a general-purpose API for end-users (it is designed as a local developer tool / MCP integration)
- • Environments requiring strict enterprise compliance without vetting dependencies and behavior
Interface
Authentication
The README does not describe authentication or authorization. Usage appears intended for local/desktop MCP clients where transport is stdio to a local process.
Pricing
No pricing model described; appears to be an open-source tool built and run locally.
Agent Metadata
Known Gotchas
- ⚠ Pre-beta status suggests incomplete feature coverage (hover/code actions not implemented per README)
- ⚠ Some tools require an explicit `language` argument; relying on file-extension routing may fail for unconventional file types
- ⚠ Edits apply to files based on extension-based language detection; mismatched extensions or language configs could route edits to the wrong LSP
- ⚠ No described cancellation/context-handling improvements yet; long-running LSP calls could lead to slow/blocked agent steps
- ⚠ Because it can execute code lens actions and apply text edits, the agent should constrain requested edits to intended files/regions to reduce accidental large changes
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-language-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-04-04.