Measures the fraction of retrieved RAG context chunks that are relevant to the question, providing a precision score to diagnose retriever noise and quality.
Apache 2.0
699,399 tools. Updated 2026-10-24 18:54
"A tool or method for searching a codebase and providing relevant context" matching MCP tools:
- Execute multi-step AI workflows with reduced context usage by keeping intermediate results in the workflow engine, supporting multiple model calls and tool integrations.MIT
- Discover available API toolsets with descriptions, tool counts, and examples to identify relevant tools before searching.MIT
- Create a semantic index of a codebase to unlock intelligent search. Run this first to enable code queries.Apache 2.0
- Get relevant context about a topic from past sessions to guide current conversations.Business Source 1.1
- Explain a specific code concept or section by searching with a focused query and optional file filter, returning tight context.MIT
Matching MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.1MIT
- AlicenseAqualityDmaintenanceMCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.11MIT
Matching MCP Connectors
Let your AI agent build, preview and update web apps, download source and publish when you allow it.
Indicative UK skip hire prices by town, council skip permit rules and skip size recommendations.
- Retrieve relevant memories for user queries to fetch prior context, preferences, and facts before responding.MIT
- Deploy files directly to Cloud Run by providing their contents in a chat context. Specify filenames and content for quick deployment without local file storage.Apache 2.0
- Update a route by providing its UUID and optional controller, method, path, and context fields to wire it to a controller method.MIT
- Analyze your codebase to identify which threats from your threat model are already mitigated, and generate a markdown validation report.Apache 2.0
- Search a local knowledge graph via BFS or DFS to return relevant nodes and edges as text context for broad questions or specific path tracing.Apache 2.0
- Recursively scan an MCP server codebase to find insecure tool-definition patterns; skips node_modules, .git, dist, and binary files.MIT
- Create a method in a file with optional visibility, static, async, return type, parameters, and body. Includes context fields for summary, rationale, and references.MIT
- Search a repository's code graph with BFS for broad context or DFS to trace paths, returning relevant nodes and edges as cited text within a token budget.Apache 2.0
- Delegate thinking, planning, and real-time web or Twitter/X search tasks to Grok by providing relevant context, files, and prompts for accurate responses.MIT
- Doubt every decision in a plan, resolve with real evidence from codebase or web, and flag remaining doubts for human review until the plan has no load-bearing doubts.MIT
- Semantically search a codebase to find relevant code snippets with file paths and line numbers, reducing token usage by returning top matches instead of full files.MIT
- Retrieve prior engineering learnings relevant to your current task by searching with keywords and filtering by tags, impact, or status.Business Source 1.1
- Generates suggestions for improving your app (UX, performance, retention) and your idea (positioning, monetization) by analyzing project context or codebase.MIT
- Search the Jambavan index for code symbols and snippets relevant to a query. Returns a ranked, token-budgeted context block of matching functions, classes, and types to inject into prompts.MIT
- Save session-specific learnings like file locations and method behaviors for quick recall, surviving context compaction until the session ends.MIT