Data & Search

Turn any OpenAPI/Swagger spec into MCP tools. Zero config, zero code.

Detects GTM hiring activity from company career pages via Greenhouse, Lever, Ashby. Clay-ready.

Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail.

Model Context Protocol server providing secure, read-only access to Butlr occupancy and asset data

Verify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.

MCP server & CLI: codebase index + cache for Claude Code, Cursor, OpenAI Codex, Google Antigravity/Gemini. Model Context Protocol tools (codetree_read, codetree_search, …), hooks on Claude, rules on other IDEs. Token savings, SQLite index, symbol search,

Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

Cited, OSV-gated, injection-hardened web briefs for coding agents. Verified, never raw web.

Persistent code indexing for AI assistants. 50x less context than grep. 11 languages.

Local-first MCP server that gives AI tools semantic memory of your codebase.

Access 21+ social media platforms through one unified API. Profiles, posts, search.

Semantic code retrieval MCP Server — natural language → relevant code snippets, with incremental sync and file watching

Persistent, interactive MCP Apps — the AI builds an app once, you both reuse it

Adaptive error memory and code intelligence system with Hebbian synapse network, hybrid search, and REST API

SQLite MCP — query databases, inspect schemas, explain queries, export data.

Canonical Squidlor oracle tool definitions, execution and result enrichment — shared by the MCP server and the oracle-chat agents so a tool exists in exactly one place.

Crystallize headless commerce tools for AI agents via Model Context Protocol

Local post-hoc forensics and postmortems for coding-agent runs

Local-first, LLM-agnostic memory layer for AI assistants.