Skip to main content
Glama

Cursor Conversations MCP Server

by vltansky

search_conversations

Search Cursor chat content using exact text matching to find specific technical terms, error messages, or code patterns in conversations. Avoid using for project-specific searches.

Instructions

Searches through Cursor chat content using exact text matching (NOT semantic search) to find relevant discussions. WARNING: For project-specific searches, use list_conversations with projectPath instead of this tool! This tool is for searching message content, not project filtering.

WHEN TO USE THIS TOOL:

  • Searching for specific technical terms in message content (e.g., "useState", "async/await")
  • Finding conversations mentioning specific error messages
  • Searching for code patterns or function names

WHEN NOT TO USE THIS TOOL:

  • ❌ DON'T use query="project-name" - use list_conversations with projectPath instead
  • ❌ DON'T search for project names in message content
  • ❌ DON'T use this for project-specific filtering

Search methods (all use exact/literal text matching):

  1. Simple text matching: Use query parameter for literal string matching (e.g., "react hooks")
  2. Multi-keyword: Use keywords array with keywordOperator for exact matching
  3. LIKE patterns: Advanced pattern matching with SQL wildcards (% = any chars, _ = single char)
  4. Date range: Filter by message timestamps (YYYY-MM-DD format)

IMPORTANT: When using date filters, call get_system_info first to know today's date.

Examples: likePattern="%useState(%" for function calls, keywords=["typescript","interface"] with AND operator.

Input Schema

NameRequiredDescriptionDefault
endDateNoEnd date for search (YYYY-MM-DD). Note: Timestamps may be unreliable.
includeCodeNoInclude code blocks in search results
keywordOperatorNoHow to combine keywords: "AND" = all keywords must be present, "OR" = any keyword can be presentOR
keywordsNoArray of keywords for exact text matching - use with keywordOperator to find conversations with specific combinations
likePatternNoSQL LIKE pattern for advanced searches - use % for any characters, _ for single character. Examples: "%useState(%" for function calls, "%.tsx%" for file types
maxResultsNoMaximum number of conversations to return
outputModeNoOutput format: "json" for formatted JSON (default), "compact-json" for minified JSONjson
queryNoExact text matching - searches for literal string occurrences in MESSAGE CONTENT (e.g., "react hooks", "useState", "error message"). ❌ DON'T use for project names - use list_conversations with projectPath instead!
searchTypeNoFocus search on specific content types. Use "project" for project-specific searches that leverage file path context.all
startDateNoStart date for search (YYYY-MM-DD). Note: Timestamps may be unreliable.

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "endDate": { "description": "End date for search (YYYY-MM-DD). Note: Timestamps may be unreliable.", "type": "string" }, "includeCode": { "default": true, "description": "Include code blocks in search results", "type": "boolean" }, "keywordOperator": { "default": "OR", "description": "How to combine keywords: \"AND\" = all keywords must be present, \"OR\" = any keyword can be present", "enum": [ "AND", "OR" ], "type": "string" }, "keywords": { "description": "Array of keywords for exact text matching - use with keywordOperator to find conversations with specific combinations", "items": { "minLength": 1, "type": "string" }, "type": "array" }, "likePattern": { "description": "SQL LIKE pattern for advanced searches - use % for any characters, _ for single character. Examples: \"%useState(%\" for function calls, \"%.tsx%\" for file types", "type": "string" }, "maxResults": { "default": 10, "description": "Maximum number of conversations to return", "maximum": 50, "minimum": 1, "type": "number" }, "outputMode": { "default": "json", "description": "Output format: \"json\" for formatted JSON (default), \"compact-json\" for minified JSON", "enum": [ "json", "compact-json" ], "type": "string" }, "query": { "description": "Exact text matching - searches for literal string occurrences in MESSAGE CONTENT (e.g., \"react hooks\", \"useState\", \"error message\"). ❌ DON'T use for project names - use list_conversations with projectPath instead!", "type": "string" }, "searchType": { "default": "all", "description": "Focus search on specific content types. Use \"project\" for project-specific searches that leverage file path context.", "enum": [ "all", "project", "files", "code" ], "type": "string" }, "startDate": { "description": "Start date for search (YYYY-MM-DD). Note: Timestamps may be unreliable.", "type": "string" } }, "type": "object" }

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/vltansky/cursor-conversations-mcp'

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