Skip to main content
Glama
project-numina

lean-lsp-mcp

by project-numina
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Related Servers

Alternatives to lean-lsp-mcp

No user-submitted related servers found.

    Related Servers

    • logosphere

      jdhart81
      A
      license
      Not graded
      quality
      B
      maintenance
      Provides an MCP server for building inspectable reasoning graphs, capturing arguments and evidence, and verifying conditional conclusions using Lean.
      Apache 2.0

    • Lean LSP MCP

      oOo0oOo
      A
      license
      A
      quality
      A
      maintenance
      Enables LLM agents to interact with the Lean theorem prover through the Language Server Protocol, providing tools for analyzing Lean projects, accessing diagnostics, goal states, documentation, and searching for theorems using both local and external search services.
      23
      503
      MIT

    • lsp-mcp

      afriemann
      A
      license
      Not graded
      quality
      B
      maintenance
      An MCP server that exposes LSP-backed code navigation and editing tools to LLM agents using a single global config file to route file extensions to language servers.
      MIT

    • rocq-piler

      scidonia
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that bridges LLMs with the Rocq (Coq) proof assistant via LSP, enabling interactive theorem proving with AI.
      8
      Apache 2.0
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 21 tools

    Disambiguation2/5

    Multiple search tools (lean_local_search, lean_leandex, lean_loogle, lean_leanfinder, lean_state_search, lean_hammer_premise) have overlapping purposes, differentiated only by backend or exact query type. The informal prover tools (gemini_informal_prover, gpt_informal_prover, discussion_partner) are nearly interchangeable, causing boundary confusion.

    Naming Consistency3/5

    The core tools consistently use the lean_ prefix, but the AI tools break the pattern with gemini_, gpt_, and discussion_partner. Verb-noun and noun-only names are mixed (e.g., lean_build vs lean_goal), creating moderate inconsistency.

    Tool Count3/5

    At 21 tools, the server is on the heavy side but each tool serves a niche purpose. The count is justified by the breadth of Lean development and search needs, though some redundancy inflates the count.

    Completeness4/5

    Core Lean workflows are well covered: file outline, diagnostics, goals, hover, completions, build, and run code. Search is extensive, and AI integrations fill the gap for proof strategy. Missing direct file editing is minor since edits happen outside the server.

    Maintenance

    ActivityInactive
    ResponsivenessNo issues

    Resources