Skip to main content
Glama
contextstream

ContextStream MCP Server

search

Search workspace memory and knowledge using multiple modes including semantic, keyword, and regex matching to find relevant information across projects.

Instructions

Search workspace memory and knowledge. Modes: auto (recommended), semantic (meaning-based), hybrid (legacy alias for auto), keyword (exact match), pattern (regex), exhaustive (all matches like grep), refactor (word-boundary matching for symbol renaming), team (cross-project team search - team plans only).

Output formats: full (default, includes content), paths (file paths only - 80% token savings), minimal (compact - 60% savings), count (match counts only - 90% savings).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoSearch mode (auto recommended; hybrid is a backward-compatible alias)auto
queryYesSearch query
workspace_idNoWorkspace ID (UUID).
project_idNoProject ID (UUID).
limitNoMax results to return (default: 3)
offsetNoOffset for pagination
content_max_charsNoMax chars per result content (default: 400)
context_linesNoLines of context around matches (like grep -C)
exact_match_boostNoBoost factor for exact matches (default: 2.0)
output_formatNoResponse format: full (default), paths (80% savings), minimal (60% savings), count (90% savings)

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/contextstream/mcp-server'

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