"How to build your own knowledge base" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
formcarry handles everything after your form is submitted: it emails you, auto replies to the person who submitted, filters spam, and delivers webhooks. You write the HTML form and set its action to a URL formcarry gives you. An agent can create a form, wire the emails and webhooks, and answer questions about the submissions, like how many signups last week.
Contract-change authorization for AI agents: preflight a change to an API or MCP contract, get a signed decision, and verify the receipt offline. Only a granted change can proceed.
Kristo Intelligence API MCP Server - onchain DeFi signals for Base. Get bot status, market stats, and onchain sales via x402 payments.
Crawl and scrape websites to clean markdown, and track what changed between crawls.
Kaiva Bridge turns an OpenAPI spec, API docs link, database, spreadsheet or documents into a hosted MCP server. Every tool starts switched off and you choose which ones to expose. Teammates connect from Claude or ChatGPT by signing in with OAuth; your API credential is stored encrypted and never shown to the AI. Free plan: 3 servers and 200,000 tool calls a month, no card. Pricing: https://kaiv.ai/bridge/pricing Security: https://kaiv.ai/bridge/security Docs: https://kaiv.ai/bridge/docs
Coding agents in multi-service codebases routinely rebuild existing helpers, trust stale type definitions, and modify API contracts without knowing who consumes them. Carrick solves this by indexing your entire TypeScript ecosystem across service and repository boundaries. By integrating deeply with the TypeScript compiler, Carrick traces every route, type, and cross-service call while recording function behaviour so agents search by intent rather than name. Delivered via MCP for AI agents and LSP for IDEs, Carrick ensures models see existing endpoints and utilities before generating new code. The scanner is source-available and runs from your CLI or CI pipeline.
AI agents run business processes on your business data. Every change is attributed and reversible.
Publish websites from your AI chat, edit, restore versions and check visitor stats. Live in seconds.
Connect Claude, ChatGPT, Cursor or any MCP client to Ybug. Read bug reports with screenshots, console logs and network requests, then triage them in chat.
Deterministic SHA, HMAC, Base64 and JWT decode tools with prepaid direct-USDC API credits on Base.
Prove end users to agents and apps: login-links, OIDC clients, and API keys over remote MCP
AETumi MCP - Three.js/WebGL 3D web scenes, components & templates you own the source of.
Search the mcp.tc directory of MCP servers from your assistant. Find servers by name, task or category, then get each one's own URL or install command, sign-in type, tools, recent tool changes and setup steps for your client. Read-only, no sign-in.
Drive and test your React Native and Expo apps end-to-end on iOS and Android. Supports real devices, simulators, and emulators. Snapshots, taps, typing, swipes, screenshots, deep links, reloads, builds and runtime errors.
Let cloud agents talk to you: progress updates spoken on your Mac, and replies you send back.
Finds the GitHub Actions workflow eating your CI bill and suggests fix diffs, verified against runs.
Scores code against a repo's own incident history, rolled into an 8 index Production Reliability Index (PRI). Exposes suggest_code, save_recommendation, and get_scan_report as tools.
Create 3D device mockups, App Store screenshot sets and launch videos from your AI. Showoff.dev puts your screenshots on real iPhones, Pixels, iPads and MacBooks, sets camera and background, and exports App Store and Google Play sizes. Works with Claude, ChatGPT, Cursor, Codex and any MCP client.
A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.
Fillo MCP server — provision, scaffold, publish, and query forms from your coding agent.
