Lean LSP MCP

by oOo0oOo

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

lean_run_code

Destructive

Execute self-contained Lean code snippets with imports and return diagnostics to check correctness and surface errors.

Instructions

Run a code snippet and return diagnostics. Must include all imports.

Input Schema

Name	Required	Description	Default
`code`	Yes	Self-contained Lean code with imports

Output Schema

Name	Required	Description
`success`	Yes	Whether code compiled successfully
`timed_out`	No	True if elaboration timed out (results are partial)
`diagnostics`	No	Compiler diagnostics

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.31.0Oct 3, 2026

addedOutput schema / $defs / DiagnosticCategory

Added value: +{
+  "enum": [
+    "diagnostic",
+    "linter",
+    "sorry",
+    "suggestion"
+  ],
+  "title": "DiagnosticCategory",
+  "type": "string"
+}

addedOutput schema / $defs / DiagnosticMessage / properties / category

Added value: +{
+  "$ref": "#/$defs/DiagnosticCategory",
+  "default": "diagnostic",
+  "description": "'linter' is style noise (unused variables and the like) that does not block compilation; 'sorry' marks an unproved declaration and is never noise; 'suggestion' carries a `Try this:` replacement; 'diagnostic' is everything else."
+}

addedOutput schema / $defs / DiagnosticMessage / properties / hint

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Guidance for a recognised failure mode, when one applies",
+  "title": "Hint"
+}

Changed1 schema field changedv0.28.0Jul 11, 2026

addedOutput schema / $defs / DiagnosticMessage / properties / lean_tags

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Lean-specific tags: 'unsolvedGoals' (proof incomplete here) or 'goalsAccomplished' (proof finished). Machine-readable proof status - prefer over string-matching the message.",
+  "title": "Lean Tags"
+}

Addedv0.10.0May 1, 2026
Removedv0.23.1May 1, 2026
First observedJan 26, 2026

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations flag this as destructive, non-idempotent, and open-world, but the description says nothing about side effects, what state the snippet can affect, or why execution is considered destructive. The only added constraint is the self-contained imports requirement, which is already carried by the schema. For a code-execution tool with a destructive hint, this leaves the risk profile unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no wasted words, and the core action is front-loaded before the input constraint. It is efficient, though extremely terse for a destructive operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the single parameter is fully documented in the schema. However, for a destructive code-execution tool, the definition omits where the code runs, what 'diagnostics' covers, and how it relates to sibling diagnostic tools, leaving meaningful gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is a single parameter with 100% schema description coverage, so the schema already explains that code must be self-contained Lean with imports. The description restates that requirement rather than adding format, size, or content constraints beyond it. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource: run a Lean code snippet and return diagnostics. It is distinguishable from most siblings by the 'snippet in, diagnostics out' framing, though it does not explicitly contrast itself with lean_build or lean_multi_attempt.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The prerequisite 'Must include all imports' tells the agent how the input must be formed, but there is no explicit guidance on when to choose this over lean_build, lean_multi_attempt, or lean_diagnostic_messages. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.