Tool Discovery Python Packages

install-manifest

v0.4 spec — JSON manifests that let autonomous agents install, verify, drive, and revoke tools without a human in the loop.

qveris

Bring professional data and tools to the AI you already use: open-source MCP, CLI, SDKs, skills, and docs to find services, call them, and audit usage.

slop-mcp

MCP orchestrator — connect dozens of MCP servers while exposing only 8 meta-tools, so tool definitions stop eating your context window

axiolex

Shared tool discovery and execution for AI clients and applications across MCP, A2A, and internal tools—intent-ranked Top-K retrieval with centrally managed provider and tool changes

agentnexus-client

Continuously verified registry of the APIs, MCP servers and CLIs that AI agents call — live health checks, reliability history, and an anonymous MCP endpoint agents can connect to without a consent screen.

tool-compass

Semantic MCP tool-discovery gateway — find tools by intent, not memory.

sift-tools

Give LLM agents 2 meta-tools instead of a 30k-token tool catalog - hierarchical, search-first tool discovery with an active tool request, hybrid retrieval, response filtering and code mode. Works with OpenAI/Anthropic/LangChain/MCP. pip install sift-tools

snap-router-mcp

Task-to-tool discovery over the merged x402 Bazaar + MCP Registry catalog — one fast pass, no LLM call.

semantic-tool-router

Runtime semantic discovery for agent tools