"A semantic search router for dynamically discovering and routing MCP tool definitions" matching MCP servers:

Enables agents to send only the handful of tool definitions relevant to each question, ranking a large catalog by keywords and optional embeddings to cut context cost and wrong-tool picks. It can also run in front of any mcpServers config as a proxy that exposes just search_tools and call_tool instead of the whole catalog.

Provides semantic code search over codebases using local embeddings with natural language queries. Supports hybrid search, file watching, and respects .gitignore.

Indexes codebases using semantic embeddings for natural language search, enabling developers to find code with queries like 'how does authentication work'.

Enables AI coding agents to perform semantic code search locally, finding code by meaning rather than exact keywords.

Routes external MCP tools behind a small on-demand discovery interface for Codex agents, using Jev to select relevant tools and providing fallback to the full inventory when confidence is low.

Enables semantic code search over local repositories, providing tools like semantic_search and list_indexed_repos to Claude Code, so users can find relevant code sections via natural language instead of grep.

Provides AI assistants with instant access to TypeScript type definitions from your project dependencies. Enables generation of complete, type-safe mocks and test data by automatically discovering and exposing interface structures from node_modules.

Enables AI agents to perform semantic search over codebases by converting natural language queries into efficient search patterns like grep and ripgrep. It utilizes LLMs to verify relevance and find code snippets that traditional keyword-based searches might miss.

Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids, grades sides blind with one judge per vendor, and tracks per-kind standings and lane pacing.

Provides AI coding agents with structured access to indexed codebases via semantic search, symbol analysis, and file reading tools.

Enables LLMs to perform addition calculations through a stdio-based MCP server with an add_numbers tool and type-safe validation.

Enables dynamic tool discovery and loading for Claude using BM25, regex, and semantic search algorithms. It supports managing a catalog of over 10,000 tools with minimal context overhead and provides a REST API for tool management.

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

Enables MCP clients to chat through multiple LLM API keys with automatic rotation and failover, discover free and available models, inspect key health and routing, refresh catalogues, ensure a local proxy, and generate OpenCode/Kiro/skill configuration.

A lazy router for Claude Code skills that exposes a library of skills through search, load, and reindex MCP tools, reducing context usage by only loading skills on demand.

Semantic navigator for MCP tools that finds relevant tools by natural language intent, reducing token usage by 95%.

Enables agents to search a local catalog, load skills, inspect MCP tool schemas, and invoke selected tools through a single unified MCP tool, reducing per-request overhead.

Aggregates and routes to hundreds of downstream MCP servers behind a single interface, exposing only five meta-tools and dynamically retrieving the relevant tool for an agent on demand.

Automatically selects the optimal LLM model for each task in Cursor IDE by analyzing query complexity, task type, and applying customizable routing strategies across 17 different AI models.

Enables efficient tool routing and context budgeting for AI agents handling hundreds of MCP tools, with circuit breaker, RBAC, and federation for reliable serving.

Enables AI agents and their users to submit, route, and monitor training jobs across free-tier GPU clouds (Kaggle, Colab, Lightning, local MPS) through a local daemon that tracks quota, explains routing decisions, and gates long or secret-reading agent jobs behind human approval.

A Model Context Protocol server that provides a scratchpad tool for LLMs to organize thoughts, take notes, and plan approaches to complex problems.

Enables AI agents to perform semantic code search across entire codebases using natural language queries. Provides fast indexing and ranked search results with line numbers and file paths through the Seroost search engine.

Enables repo-scoped expert consultation from Claude Code by compressing difficult questions into structured briefings and routing them through ai-browser-bridge to ChatGPT web, with per-project activation and safeguards.

Exposes a governed semantic layer to AI agents so they select metrics and dimensions from a closed, engineer-declared vocabulary instead of writing SQL. Validates every typed call against the contract, rejects out-of-contract requests with structured errors and suggestions, and returns query rows together with the compiled SQL and dbt lineage for auditing.

This MCP server lets agents route natural-language requests to the best matching workflow or tool using weighted lexical scoring and two-gate abstention. It returns ranked candidates with match evidence or explicitly refuses when confidence or score falls below calibrated thresholds.

Encoding-aware, indentation-smart file tools for AI coding agents. 20+ tools including read/edit with automatic encoding detection, smart indentation conversion, SSH, SFTP, process management, and system utilities.

Enables project-scoped agent memory backed by a per-project SQLite index and raw data store, plus a global registry for discovering local memory workspaces. Agents can search summaries, retrieve original records on demand, save new memories, and link related records without sharing memory across projects.

Enables agents to connect through a single gateway that has a decision model pick which MCP tools and playbooks are relevant to each request, so the LLM only sees the few schemas it needs, and to then invoke those tools on the underlying servers. This cuts tool-selection cost and prompt size dramatically when many MCP servers are connected.

A tool discovery MCP server that integrates with Azure DevOps wikis and code-graph-rag to match natural language goals to tools, enabling tool composition and proxy testing.