Skip to main content

Tools Reference

Each MCP server can include between 3 and 10 tools. Here's the complete list.

ToolDescription
search_docsFull-text search across all indexed sources. Returns the most relevant passages.
query_sourceQuery a specific source URL for targeted results.
get_code_examplesExtract code snippets and examples from your sources.
summarize_contentSummarize the content of a specific source page.
find_api_referenceFind API endpoints, parameters, and documentation.
get_changelogRetrieve release notes, changelogs, and version history.
search_issuesSearch for known issues, bugs, and their solutions.
get_quickstartGet setup guides, installation steps, and quickstart content.
extract_schemaExtract type definitions, data models, and schemas.
ask_questionNatural language Q&A across all indexed sources.

Choosing the right tools

See Choosing Tools for recommendations based on your use case.

How tools are called

When an AI agent connects to your MCP server, it sees the tools you selected in its tool list. During a conversation, the agent decides which tool to call based on the user's question. The tool executes a search against your indexed sources and returns the relevant content.

Each tool call is logged in your Dashboard with the query, tool name, sources referenced, response time, and status.