Development MCP Servers — Page 18

Semantic code retrieval over a graph of entities, relationships, changes, and provenance. Locate, search, context packs, data-flow tracing, and impact analysis without raw file search.

Google index monitoring with history. Which pages are indexed, which dropped out and when, and why the rest are not.

Tamper-evident action logging for AI agents: hash-chained ledger_append/ledger_verify MCP tools over one JSONL file, zero dependencies — proves the record wasn't altered in place (limits stated honestly in the docs).

Free hosted changelog: agents can sign up, publish release notes, and manage a public changelog page + RSS via MCP (no email or CAPTCHA needed).

Agent identity and key custody — provider keys held in a local encrypted vault and leased to agents under owner approvals, with env-var injection so secrets never enter model context and a one-command kill switch; plus a registry with Ed25519 agent identity, reputation, and messaging.

harvis.dev is zero-setup static hosting: run npx harvis in any folder and get a live URL in seconds

Mechanical citation and claim checks for AI-generated documents — counts, references, totals; located verdicts, no model on the free path, documents never stored.

Live infrastructure checks over MCP: domain health (SSL/DNS/reachability), MCP server health with A–F security posture, AI agent-readiness, email blacklist, broken links, and live status for 11 major cloud vendors — 8 tools, no signup.

Turn any OpenAPI 3.0 spec into an MCP server with zero code — deploy to Cloudflare Workers, Node.js, Docker, or run locally via npx, with a built-in OAuth 2.1 server for MCP clients that require custom connector authentication.

Pipehero tunnels your localhost to a public URL and captures every webhook, so you can inspect, replay, and debug them — including from your AI agent via MCP.

Verified GPU compute for humans, applications, and agents.

Secure Docker monitoring and management MCP server for containers, logs, alerts, diagnostics, and safe control across local and remote hosts.

Paid MCP tool store — register your own MCP server and keep 80% of revenue per call. Billing, auth, and abuse protection handled by teai.io.

Publish pages to a live URL and run skilled AI agents from your terminal.

Fail-closed CI gate for AI-written code: blocks known CVEs and serves human-approved acceptance criteria to Claude Code/Cursor/Codex over MCP, read-only to the agent.

Build Elementor sites with AI agents — ~90 tools for native, editable Elementor V4 pages over REST, with validation, backups, rollback, and a typed JSX compiler. MIT.

Use KPainter's remote MCP server to create source-grounded videos, slides, and interactive knowledge content from your own materials.

Remote MCP server (Streamable HTTP) at https://mcp.agenticrail.nz/ — deterministic step-order enforcement for AI agents. evaluate_step returns ALLOW or DENY before a step runs; verify_receipt proves a sequence's Ed25519-signed, hash-chained receipt chain is intact. No auth required: omit the bearer token and calls run on the public demo key. That first clause matters — the form has no "remote/hosted" field, and putting the endpoint in the description is the convention on that list ("Fully REMOTE! Just use…"). The rest mirrors your own server card verbatim, so the listing and the card can't drift.

MCP Studio gives you a no-code way to turn docs, repos, websites, PDFs, and MCP endpoints into reliable context your AI tools can use. Build MCP servers in minutes and track usage, answer quality, and business impact with built-in analytics.

Minimal TypeScript MCP teaching server with two bounded in-memory tools, Zod validation, official SDK protocol tests, CI, and no file, network, subprocess, or secret access.

Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.

Traces which neurons and attention heads drive a language model's output via MCP tools, built on TransformerLens.

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.

Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.

MCP-based SSH session manager for Linux backend teams

Sends the same prompt to multiple LLM providers in parallel and returns a divergence score.

Fail-closed deterministic checks and tamper-evident receipts for AI agent outputs.

Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.

Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.