MCP Servers

Asks 8 AI crawlers for your page, checks who really answered, and writes the fixes. MIT.

Capture HTTP, email, and DNS callbacks with webhook.site from MCP clients.

Read-only cross-cutting analysis, metrics, and reporting across the Golden Suite.

Inclusive language scan/fix for AI and human copy. Local rules, no account.

Readback-verified FL Studio transport, mixer, channel, sequencer, and plug-in control.

Change Asana without opening Asana — custom fields, sections, start dates, rich notes, bulk. PAT.

Audit a site's UX the way a design-literate reviewer would, with a concrete fix for every finding.

Live cross-DEX pool prices, liquidity and spreads on 6 EVM chains, read from on-chain pool state.

Drive a running React Native or Expo app from inside its JS runtime: see, act, prove.

Design kits, brand naming, and domain research for coding agents.

MCP server for serial port communication. 25 tools, resources, prompts, and stdio/HTTP transports.

Team-aware memory: intent, decisions, real-time conflicts for AI coding assistants.

MCP server for The Movie Database (TMDB) with IMDb/Rotten Tomatoes/Metacritic ratings via OMDb.

Persistent code memory for AI agents: notes pinned to files and symbols that survive refactors.

Protected RAG storage — agents discover public metadata, content only by access token.

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

Safe-write Postgres MCP server with preview-before-execute writes and rollback safety.

Wisp Panel MCP server for secure game server management through the Wisp Client API.

Self-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.

Deterministic cross-repo contract analysis for AI agents: frontend calls vs backend endpoints.

Every-click AI QA: walks your whole app from a preview URL and reports broken clicks and errors.

MCP server for Juniper Networks device operations via junos-ops

MCP server for Arista EOS device operations via eAPI

Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.