Loading ToolBench
Model Context Protocol integration for Claude Context - provides semantic code search and indexing capabilities for codebases
This MCP server exposes 9 tools with mixed definition quality. While tool schemas are mostly present and descriptions exist, there are significant gaps in parameter documentation, missing output schema specifications, and limited error handling guidance. The server includes both semantic code search tools (index_codebase, search_code, clear_index, get_indexing_status) and file system utilities (edit, search_text, read_file, list_directory, directory_tree). Most tools have descriptions, but many lack parameter-level detail and actionable error messages. Tool naming is generally verb-based but some tools lack clarity on composition and idempotency. No tool demonstrates per-parameter descriptions for all fields, and output schemas are not documented for any tool.
Clear the search index. IMPORTANT: You MUST provide an absolute path.
Generates a tree structure of a directory.
Edits the specified file with the given modifications. This tool marks files that need to be edited with the specified changes.
Get the current indexing status of a codebase. Shows progress percentage for actively indexing codebases and completion status for indexed codebases.
Index a codebase directory to enable semantic search using a configurable code splitter. ⚠️ **IMPORTANT**: - You MUST provide an absolute path to the target codebase. ✨ **Usage Guidance**: - This tool is typically used when search fails due to an unindexed codebase. - If indexing is attempted on an already indexed path, and a conflict is detected, you MUST prompt the user to confirm whether to proceed with a force index (i.e., re-indexing and overwriting the previous index).
Output schemas completely undocumented across all 9 tools. LLMs cannot predict what fields will be returned, forcing them to hallucinate field names for downstream processing.
Parameter descriptions missing or incomplete on 6 of 9 tools. Parameters like 'path', 'limit', 'offset' lack context on expected format, range, or side effects.
Error handling not documented. Tools like 'clear_index', 'read_file', 'list_directory' don't explain what happens on permission errors, missing paths, or invalid input. No recovery guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-21 | D | 57 | 2026-07-28+ | v2 |
| 2026-03-09 | D | 51 | - | v1 |
Lists the contents of a directory.
Reads the content of a text file at the specified path. You can optionally specify an offset and limit to read only a portion of the file.
Search the indexed codebase using natural language queries within a specified absolute path. ⚠️ **IMPORTANT**: - You MUST provide an absolute path. 🎯 **When to Use**: This tool is versatile and can be used before completing various tasks to retrieve relevant context: - **Code search**: Find specific functions, classes, or implementations - **Context-aware assistance**: Gather relevant code context before making changes - **Issue identification**: Locate problematic code sections or bugs - **Code review**: Understand existing implementations and patterns - **Refactoring**: Find all related code pieces that need to be updated - **Feature development**: Understand existing architecture and similar implementations - **Duplicate detection**: Identify redundant or duplicated code patterns across the codebase ✨ **Usage Guidance**: - If the codebase is not indexed, this tool will return a clear error message indicating that indexing is required first. - You can then use the index_codebase tool to index the codebase before searching again.
Searches for a regular expression pattern within the content of files in a specified directory (or current working directory). Can filter files by a glob pattern. Returns the lines containing matches, along with their file paths and line numbers.
Idempotency not declared. The 'edit' tool modifies files, is it safe to retry? Does a second edit with the same old_string/new_string fail or succeed? Agents need this information.
Tool composition unclear. 'search_code' depends on 'index_codebase', but the dependency is only mentioned in tool descriptions, not in response structure. search_code output doesn't include file paths needed for 'read_file' or 'edit'.
Path handling inconsistent. Some tools require 'ABSOLUTE path' (emphasized in caps), others don't specify. No guidance on Windows vs POSIX paths, symlink behavior, or validation.
Result limits not enforced or documented. 'search_code' has max=50, but 'list_directory' and 'directory_tree' have no limits. Large codebases could return unbounded results, exhausting token budgets.
Generic or underspecified descriptions on 4 tools ('clear_index' 45 chars, 'list_directory' 34 chars, 'directory_tree' 34 chars). These are below the 50-char baseline and lack context for selection.