Loading ToolBench

Reading the current corpus…

mcp-language-server MCP server · D · ToolBench

mcp-language-server

github.com/bryankthompson/mcp-language-server

An MCP server that bridges Language Server Protocol (LSP) servers to the Model Context Protocol, exposing language-specific code analysis and editing capabilities through MCP tools.

<=2025-11-25STDIO5 tools

52/100

Definition Quality64

Protocol Readiness47

Supportability36

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

Server defines 5 tools with explicit schemas and descriptions. Naming follows verb_noun pattern (edit_file, definition, references, diagnostics, hover). Descriptions are present but brief (10-100 chars, below the 50-200 char baseline for LLM optimization). Parameter descriptions exist but lack detail on constraints, formats, and valid ranges. No output schemas documented. Error handling is minimal, no recovery guidance or categorization. edit_file accepts complex nested objects but lacks validation rules in description. definition, references, diagnostics, and hover lack examples of expected output structure.

Tools (5)

definitionread onlysource verified62/100

Read the source code definition of a symbol (function, type, constant, etc.) from the codebase. Returns the complete implementation code where the symbol is defined.

diagnosticsread onlysource verified65/100

Get diagnostic information for a specific file from the language server.

edit_filewritesource verified68/100

Apply multiple text edits to a file.

hoverread onlysource verified63/100

Get hover information (type, documentation) for a symbol at the specified position.

referencesread onlysource verified62/100

Find all usages and references of a symbol throughout the codebase. Returns a list of all files and locations where the symbol appears.

Issues (5)

HIGHtool ↗

No output schemas documented. LLMs cannot plan downstream calls or extract required fields without knowing response structure.

edit_filedefinitionreferencesdiagnosticshover

HIGHtool-description ↗

Descriptions are too brief (10-100 chars vs 50-200 char baseline). Lack context on WHEN to use each tool and what distinguishes them from similar LSP operations.

definitionreferenceshover

HIGHconstrained-input ↗

edit_file parameter descriptions lack validation rules. No mention of line number bounds, file path constraints, or what happens if edits overlap or reference non-existent lines.

edit_file

HIGHrecovery-guide ↗

No error handling guidance. Tools do not document what errors are retryable, what user-fixable errors look like, or how to recover from failures (e.g., file not found, symbol not found).

edit_file

Recommendations

Expand tool descriptions to 100-200 chars. For each tool, add: (1) what it does, (2) when to use it vs similar tools, (3) what it returns. Example: 'definition' → 'Retrieve the complete source code definition of a symbol (function, type, constant). Use this to understand implementation details. Returns the file path, line range, and full code snippet.'
Document output schemas for all tools. Specify the structure of responses: for 'definition', return {filePath, startLine, endLine, code}; for 'references', return {locations: [{filePath, line, column, context}]}. This enables LLMs to chain tools and extract required fields.
Add validation rules to parameter descriptions. For edit_file: 'startLine and endLine must be positive integers within the file's line count. Edits are applied in order; overlapping ranges are an error.' For hover: 'line and column are 1-indexed; must be within the file bounds.'
Implement error categorization and recovery guidance. Return structured errors: {error_type: 'not_found'|'invalid_input'|'permission_denied', message: '...', suggestion: 'Try search_symbol() first'}. This guides LLM retry logic.
Add examples to parameter descriptions showing valid input. For symbolName in 'definition': 'e.g., mypackage.MyFunction or MyType.MyMethod'. For filePath: 'e.g., src/main.go or ./internal/tools/edit.go'.

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

52/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	52	<=2025-11-25	v2