Skip to main content
Glama

search

Find relevant code and documentation in your project using hybrid semantic and keyword search to answer questions about codebase structure or stored knowledge.

Instructions

Search for documents using hybrid semantic and keyword search. Use this tool FIRST when answering questions about the user's codebase, project architecture, or stored knowledge. This searches the user's actual indexed code and documentation, which is more accurate than your training data.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query text
collectionNoSpecific collection to search
modeNoSearch mode (default: hybrid)
scopeNoSearch scope: project (current), global, or all (default: project)
limitNoMaximum results to return (default: 10)
projectIdNoSpecific project ID to search
libraryNameNoLibrary name when searching libraries collection
branchNoFilter by branch name
fileTypeNoFilter by file type
scoreThresholdNoMinimum similarity score threshold (0-1, default: 0.3). Results below this score are filtered out.
includeLibrariesNoInclude libraries in search (default: false)
tagNoFilter results by concept tag (exact match)
tagsNoFilter results by multiple concept tags (OR logic)
pathGlobNoFile path glob filter (e.g., "**/*.rs", "src/**/*.ts")
componentNoFilter by project component (e.g., "daemon", "daemon.core"). Supports prefix matching.
exactNoUse exact substring search instead of semantic search (default: false)
contextLinesNoLines of context before/after matches in exact mode (default: 0)
includeGraphContextNoInclude code relationship graph context (callers/callees) for matched symbols (default: false)
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/ChrisGVE/workspace-qdrant-mcp'

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