Skip to main content
Glama
Aristotle MCP Server
by gleachkr

Aristotle MCP Server

A minimal Model Context Protocol (MCP) server for the Aristotle API, enabling LLMs to prove theorems in Lean and formalize mathematical problems.

Installation

This project uses uv for dependency management.

uv sync

Related MCP server: Lean LSP MCP

Configuration

You need an Aristotle API key. Set it in your environment:

export ARISTOTLE_API_KEY="your-api-key-here"

Running the Server

Run the server using uv:

uv run main.py

This will start the MCP server over stdio.

Tools

  • prove_lean_file(file_path): Submit a Lean file for proving. Returns Project ID.

  • prove_informal(file_path, formal_context_path): Submit a natural language problem. Returns Project ID.

  • prove_lean_code(lean_code): Submit Lean code string. Returns Project ID.

  • prove_informal_text(text, formal_context_path): Submit natural language string. Returns Project ID.

  • get_project_status(project_id, save_solution_to): Check status and retrieve solution code.

  • list_recent_projects(): List recent projects.

Resources

  • aristotle://projects: JSON list of recent projects.

  • aristotle://projects/{project_id}: Detailed status and content of a specific project.

Available Tools

6 tools
get_project_statusB

Checks the status of a specific Aristotle project. Returns full project data including solution if available.

Inputs: project_id (required), save_solution_to. Returns: result

list_recent_projectsB

Lists the most recent projects submitted to Aristotle.

Inputs: limit, save_to. Returns: result

prove_informalC

Submits a file containing natural language mathematics (Text, Markdown, LaTeX) to be formalised and proved. Returns the Project ID immediately.

Inputs: file_path (required), formal_context_path. Returns: result

prove_informal_textC

Submits natural language mathematics directly to be formalized and proved. Returns the Project ID immediately.

Inputs: text (required), formal_context_path. Returns: result

prove_lean_codeB

Submits Lean code directly to Aristotle to fill in 'sorry' placeholders. Returns the Project ID immediately.

Inputs: lean_code (required). Returns: result

prove_lean_fileB

Submits a local Lean file to Aristotle to fill in 'sorry' placeholders. Returns the Project ID immediately.

Inputs: file_path (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 6 tools

    Disambiguation2/5

    There is significant overlap between prove_informal, prove_informal_text, prove_lean_code, and prove_lean_file, as all four handle proof submission with only minor input format differences. This creates ambiguity for an agent trying to select the right tool, especially between the informal text and file variants. The get_project_status and list_recent_projects are distinct, but the core proving tools are poorly differentiated.

    Naming Consistency4/5

    The naming follows a consistent snake_case pattern throughout, which is good. However, there is a minor inconsistency: most tools use verb_noun (e.g., get_project_status, prove_informal), but list_recent_projects uses verb_adjective_noun, which slightly deviates from the pattern. Overall, the naming is mostly predictable and readable.

    Tool Count4/5

    With 6 tools, the count is reasonable for a server focused on mathematical proof automation. It covers key operations like project listing, status checking, and proof submission. However, the set feels slightly thin as it lacks tools for managing or updating existing projects, but it is well-scoped for the core workflow.

    Completeness3/5

    The tool surface covers basic submission and status checking, but there are notable gaps. For example, there are no tools to update, cancel, or delete projects, and no way to retrieve proof results beyond status. This could lead to dead ends for agents needing to manage project lifecycles, though core submission workflows are supported.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      Not graded
      maintenance
      Enables extraction of mathematical content from TeX papers and conversion to Lean code through a structured intermediate representation. Supports project scaffolding, entity management, and task tracking for mathematical formalization workflows.
      14
      -
    • A
      license
      B
      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.
      22
      81,428 PyPI
      549
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Integrates the AXLE (Axiom Lean Engine) CLI with AI assistants to provide comprehensive tools for Lean 4 proof engineering. It enables users to validate, repair, and transform Lean theorems through a remote API without requiring a local Lean installation.
      2
      -