Skip to main content
Glama
Code-Fundi

Code-Fundi MCP Server

Official
by Code-Fundi

code-fundi-search

Read-only

Search Code-Fundi repositories with semantic search, grep over docs, or grep over code. Returns matching files with similarity scores, paths, and optional documentation.

Instructions

Search across indexed Code-Fundi repositories using semantic search, grep over docs, or grep over code. Returns matching files with similarity scores, paths, and optional documentation. Use scan_mode to choose between semantic (vector), grep_docs (substring on documentation), or grep_code (substring on source code).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query string
scopeNoSearch scope (default: all)
fieldsNoDocumentation detail level per result (default: full).
repo_idsNoFilter by repository UUIDs
max_linesNoMaximum file line count
min_linesNoMinimum file line count
repo_urlsNoFilter by repository clone URLs
scan_modeNoSearch mode (default: semantic)
file_pathsNoFilter by file path patterns
file_typesNoFilter by file extensions (e.g. ['.ts', '.py'])
visibilityNoRepository visibility filter
dependenciesNoFilter by declared dependencies in code summaries
has_functionsNoOnly return files that define functions
function_namesNoFilter by function names in code summaries
similarity_thresholdNoMinimum similarity score (0-1)
Behavior4/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses the output structure (similarity scores, paths, optional documentation) and explains the difference between vector-based semantic search and substring grep modes. This adds useful behavioral context without needing to restate the annotation flags.

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

Conciseness5/5

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

The description is two sentences with front-loaded purpose and a concise explanation of the mode selection mechanism. Every clause adds meaningful information, with no redundancy or filler.

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

Completeness4/5

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

For a 15-parameter tool with no output schema, the description adequately summarizes the core function and return format while leaving filter details to the schema. It does not cover edge behavior like pagination or result limits, but given the open-world hint and read-only nature, this is acceptable.

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

Parameters4/5

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

The input schema already describes all 15 parameters with 100% coverage, setting a baseline of 3. The description adds value by explaining the scan_mode enum values semantically (semantic vector search vs substring on docs/code) and clarifying the return payload, going beyond mere parameter listings.

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

Purpose5/5

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

The description clearly states the tool performs searches across indexed Code-Fundi repositories, with three distinct modes (semantic, grep_docs, grep_code) and returns matching files with similarity scores/paths/docs. This distinguishes it from sibling list/file retrieval tools and directly conveys the action and target.

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

Usage Guidelines4/5

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

It provides explicit guidance on selecting scan_mode for the three search types, which teaches the agent when to use each mode. However, it does not contrast this tool against sibling tools such as code-fundi-list-files or code-fundi-file-docs, so the alternative guidance is incomplete.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Code-Fundi/code-fundi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server