Tool
Source-linked workflows that name MCP. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
Official CodeBuddy MCP docs show how to add local or remote MCP servers with codebuddy mcp add, pick user/project/local scopes, approve project servers, and lock tools with mcp__server__tool allow/deny rules.
Three-iteration case study: starting from an MD/spec, using CodeBuddy in VS Code, then adding MCP so each step is verified—useful pattern for internal admin tools that must match official API docs.
Show HN: Statewright's Rust engine enforces plan/implement/test states for Claude Code (and other CLIs) via MCP hooks—wrong tools are blocked structurally, shrinking death spirals for both small and frontier models.
CPA Timothy hooked GrokBot to Gmail, Calendar, iMessage, and a custom MCP CRM so the daily brief flags open ID requests, drafts email/text replies, watches lead inboxes on a weekday routine, and confirms invites when clients reply.
Adam keeps HA automations in git; Claude Code uses an MCP server to search entities, read traces, edit YAML, scp to the hub, reload, and commit—fixing a noisy camera automation in under two minutes.
Open Deep Research provides a public LangGraph implementation with separate research, summarization, compression, and report roles, configurable search providers, MCP support, and an evaluation workflow.
Show HN: `npx subagent-reuse --setup` adds an MCP that scans ~/.claude/projects/, builds SHA-256 Merkle trees of files each subagent already read/modified, and route_task decides REUSE vs CREATE_NEW before spawn—structural overlap only, no embeddings; ~1k LOC JS + 52 tests.
Show HN (Oct 17): RugSnare pins each MCP tool's {name, description, inputSchema} by canonicalized SHA-256 at install, then diffs upgrades across 24 popular servers (~3.6M weekly installs)—336 contract changes found; grades BREAKING/LOOSENED/EXPANDED/NOTATION/COSMETIC and exits 1 for CI. Apache-2.0, zero npm deps; OWASP MCP Security Cheat Sheet now recommends contract pinning.
MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
Show HN (Oct 16): Stoke Money is a personal-finance app centered on projected cash flow (not budgets); Pro adds MCP so Claude/ChatGPT can import PDFs, categorize trips, and plan transfers against the forecast—read-only or read/write scopes, revoke anytime; Plaid sync, AES-256 at rest.
Show HN (Oct 16): Things to Do ships REST + HTTP MCP so agents query SF Bay Area shows, pop-ups, concerts, and festivals in plain language (`claude mcp add --transport http thingstodo https://api.thingstodoapi.com/mcp`) instead of slow web search or ad-hoc scraping; NYC/LA listed as soon.
ConnectorBay is a live directory of hundreds of free, keyless, read-only remote MCP+REST connectors (GitHub, CI, CRM, weather/Careers/Skyward, etc.) for personal agents like Muse—nothing stored, fails with structured errors, Streamable HTTP MCP; optional Pro keys raise rate limits.
XERJ is an Apache-2.0 Rust single-binary AI-native search engine: `xerj autoindex` turns code/docs/logs/PDFs into ES-compatible indices; `xerj init` registers MCP + a short skill for Claude Code/Cursor; agents get passage search, hybrid retrieval, and namespaced memory instead of dumping whole files—trending hard on GitHub (~7k stars) with agent-oriented llms.txt.
Local-first Apache-2.0 CLI for Claude Code/Codex/Cursor: mcp-xray ranks bloated tool schemas, sync compresses CLAUDE.md↔AGENTS.md↔Cursor rules, and shield fails CI on leaked keys/prompt-injection/Trojan Unicode—claims large cuts in model-visible prompt size without API calls.
Mirror is Reflection's early-beta coding agent for the terminal—defaults to Beam-1.0-501B-A23B, manual/auto tool approval, resumable conversations, parallel /worktree agents, AGENTS.md+skills+MCP/extensions, with provider keys kept out of the agent's shell environment.
MCP gateway is GA in Red Hat Connectivity Link 1.5 with tenant isolation, progressive tool discovery (discover_tools/select_tools), 2026-07-28 stateless HTTP support, NeMo guardrails on tools/call, audit logs, and Prometheus broker metrics so enterprise agents route governed MCP traffic on OpenShift.
MCP-connected runtime QA maps critical flows and entry points, then re-tests the blast radius of each Claude Code/Cursor/Codex change against live Postgres/Kafka/APIs/MCP tools—contracts, authz, OWASP, errors—before merge, with self-heal when behavior changes on purpose.
Hosted Speko MCP (mcp.speko.ai, 101 tools) lets Claude Code/Codex/Cursor create, deploy, roll back and eval voice agents, manage sessions/calls/phone numbers/knowledge bases, and migrate external configs—directory hosts expose narrower, safer tool surfaces.
Apache-2.0 Paseo runs Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity, and Muse Code in isolated worktrees from desktop, native mobile, or remote hosts—with MCP/CLI/SDK automation, plugins, and optional E2E-encrypted relay so you steer agents without changing their subscriptions.
Google’s open AX runtime declares Task/Workspace/Model manifests on Agent Substrate: sandboxed agent jobs with git/MCP/skills pre-wired, suspend/resume, and ax ssh—aimed at high-throughput cluster runs of autonomous agents, not one laptop session.
MIT-local Python skill/CLI/dashboard coordinates Claude Code, Codex, and Cursor on one project: shared registry, ack-before-work, prove bound to file fingerprints, independent (non-author) review, and cross-provider usage/balance so green tests on the wrong code cannot close a task.
Taiwan-built open-source Go daemon runs on your machine (memory/schedules/credentials stay local): if a tool is missing it writes, sandbox-tests, and registers one, then shares the library with Claude Code/Codex via MCP server mode—alternative to cloud VM agent products.
SuperCompress v2 compresses context against the query (keeps answer-critical lines verbatim): ~64% mean cut on their B5 coding-agent suite with 24/24 evidence-retention passes; MCP/plugin for Cursor/Claude Code/Codex plus hosted API and open weights.
Open-source mcp-router sits between Claude Code and many MCP servers: find_tools / call_tool / run_script stand in for hundreds of tools; on a 441-tool fleet vs six other proxies it finished 6/6 tasks at −29% tokens while peers often used more tokens or failed—Show HN + public BENCHMARK.md.
You.com shipped four skills and four MCP servers (search, contents, research, finance) into the Cursor Marketplace so a Cursor agent can query You.com mid-coding and write against live web/finance context.
NVIDIA App 11.0.9.565 ships a loopback MCP server so compatible agents (Hermes, OpenClaw, Perplexity, etc.) can list games, apply optimal settings, and control ShadowPlay/screenshots via natural language—toggle under Settings > Features > AI Agents and App Connections.
Local-first OSS DB/workspace where Claude Code/Codex/Cursor share durable records, docs, skills, and apps—writes that matter go through human review; Skill, MCP, OpenAPI, and ACP connections keep agents stateless and work durable.
Self-hosted SQLite stack (CLI+MCP+API+UI) tracks AI visibility over time, investigates search/traffic changes, and lets coding agents act on evidence (publish, submit, measure)—BYOK, open-source alternative to closed AEO tools.
Open-source local procedural memory that learns only after tests pass, then hands Claude Code/Codex/Cursor a short verified skill note on similar tasks (reported token/tool cuts in published benchmarks).
Open-source CLI+MCP (morluto/rea) lets Claude Code/Cursor inspect binaries, Electron/.NET/apps via Hopper/Ghidra/IDA, returning evidence-backed observations so agents can rebuild features from behavior without copying source.
OSS (AGPL): index a folder of Markdown notes into local SQLite, then expose search/recall/remember tools over MCP so Claude Code/Codex reuse decisions across sessions; hosted option at renor.cloud.
Rust MCP server makes Claude Code the team lead over Claude/Codex/Gemini workers; Stop-hook + asyncRewake pushes replies (~50ms) into the lead session, with a local live team UI.
ServiceNow announced AI Passport (Oct 15): cryptographically signed runtime credentials that authorize what first- and third-party AI agents and MCP servers may do in multi-agent workflows, with graduated restrict/redirect/kill-switch enforcement and NVIDIA Open Agent Safety Platform as launch partner—expected Q4 2026 with shadow AI detection and AI Cost Management.
Show HN: jevcrawl (Apache-2.0 MCP + CLI) crawls for a goal and returns only relevant passages—small Jev model picks links/passages instead of Claude in the loop; README claims ~2× answer-page hit rate vs Crawl4AI and ~10× cheaper per answer than LLM-driven crawl; tools: crawl/scrape/map.
Nous Research shipped Hermes Agent v0.22.0 (Oct 13–14, "Threshold Release"): fresh desktop opens a guided setup on free nous/welcome with no API key; one-click llama.cpp local models; Connectors page for Gmail/Linear/Notion + MCP; 600 reviewed plugins; signed desktop (incl. Microsoft Store); codebase −34% lines with on-demand tools cutting schema tokens ~half.
Standalone Avior on the SolarWinds Platform lets IT teams define measurable goals, coordinate specialized agents across hybrid estates, and act under risk-tiered autonomy (dangerous steps need human approval) with audit trails, rollback, data masking, least-privilege tools, and MCP to third-party systems—available via guided onboarding from Oct 14, 2026.
Agentic Reliability Center GA gives one metered telemetry+LLM door, shared operational memory, and human-in-the-loop policy gates; new MCP lets Claude Code/Cursor/Codex investigate incidents from the IDE while inheriting audit trails and approval gates.
Enterprise GA for cg-oci, cg-apk, cg-versions, and cg-api so Claude Code/Cursor agents verify image tags, Wolfi package equivalents, EOL status, and org policy/attestations via browser OAuth or chainctl—server-side caps instead of prompt guardrails.
Official Pantheon MCP lets Claude Code/Cursor/Desktop inspect workspaces, sites, environments, builds, deploys, runtime logs, upstreams and secrets under your Pantheon identity; reads by default, state-changing tools pause for explicit approval; no deletes in beta.
Single Rust binary indexes calls/imports with tree-sitter, stores project/session memory in one SQLite file, and serves cited line-anchored excerpts over MCP—setup wires Claude Code/Codex/Cursor; reported 3–22× faster extracts vs Graphify on 13 codebases.
Merlin dispatches team asks from Slack/Linear/GitHub to Claude Code or Codex already signed in on teammates’ machines—reuse local repos, MCP servers, and skills with no extra model API bill; results return in the same thread, with shared skills, schedules, and workspace memory.
Open-source TypeScript beta for agentic apps: define a capability once and expose it to UI, agent, HTTP, CLI, MCP, and A2A so Claude/ChatGPT/Cursor can call the same actions humans click—skip screen-scraping computer-use for lower tokens.
Octopus Cloud ships a built-in HTTP MCP at /mcp so coding agents can list spaces/projects, check PR deployment status, create/promote releases, run runbooks, search task logs and audit events—no per-machine local MCP to install; Server gets it in 2026.3.
Magic Patterns’ MagicOS is an infinite canvas for PRDs, GitHub context, screenshots, and side-by-side UI variants; pick a winner and hand it to Claude Code, Cursor, Codex, or any MCP-compatible coding agent instead of losing the design journey in a linear chat log.
HN (Ted Haley): Pensieve locally indexes code, docs, and past agent sessions (watches repos/worktrees/uncommitted edits), exposes MCP search so Claude Code/Codex/Cursor get the few relevant passages with file:line instead of multi-round grep; Qwen3-Embedding-0.6B + SQLite/trigram + turbovec; macOS-focused OSS.
Anomaly OpenCode 2.0 (Oct 12; changelog still shipping 2.0.x Oct 16): auto-started local background service shared by TUI/web/desktop; rewritten API + @opencode/client; @opencode/codemode turns MCP/OpenAPI into scriptable functions (all MCP servers default to Code Mode); background subagents + async shell; 80+ hot-reload plugins; @opencode/sdk for embed. Upgrade: `opencode upgrade --major`.
ExcaliClaw’s hosted Streamable HTTP MCP (https://excaliclaw.com/mcp) lets Claude Code/Desktop, Cursor, Codex, VS Code, OpenCode and OpenClaw list/create/update diagrams, ER/flowcharts, collections, PNG/SVG export, and live canvas collab under browser OAuth—unlimited MCP on all plans; launched on Product Hunt around Oct 12, 2026.
Stable open-source Azure MCP 3.0 adds Backup, Resilience, SRE Agent, Terraform/Advisor, Monitor/Cosmos/IoT toolsets plus clearer schemas, --learn, and secure-by-default resource creation so Copilot/Cursor/Claude agents can inspect and plan Azure work with predictable contracts.
At Gemini at Work 2026 Google announced the Gemini agent—one interface for Q&A, knowledge work, media, and coding that plans outcomes, spawns temporary sub-agents or persistent coworker agents (@agents.company.com), keeps multi-type memory, connects via tools/MCP/skills registries, and routes across Gemini and Claude with spend caps and Agent Gateway policy.
OutSystems MCP is GA on every ODC tenant: Claude Code/Codex/Cursor/Kiro can hand work to Mentor for apps/agents/workflows/libraries, query the estate, publish/promote/roll back, and keep ODC roles, approvals and audit—install from github.com/OutSystems/outsystems-mcp.
MCP server plus local hooks route agent-written commits, PR text, emails and support replies into one editable queue; you rewrite and approve, then the agent sends exactly your version—Claude Code tested; Codex/Gemini/Copilot/Cursor installer-configured; free tier then paid.
Remote MCP at anaconda.com/api/mcp returns package facts, curated CVEs, org channel policy, and forum hits so Claude Code/Cursor/Codex/Kilo check real conda names and vulns before proposing installs—server cannot mutate your machine; agent still runs conda under your permissions.
Open-source MIT guardrail tracks audience×trust labels across tool calls (algebra, not LLM-as-judge), returns remedy plans (sanitize/authority/subagent) so agents keep ~90% task completion with 0% exfil on their benches—plugs via pre/post tool hooks; docs also as MCP.
An X post describes an engineer's Grok Bot template that starts from an API's data shapes, builds an MCP-and-skills scaffold, and proves the resulting Cursor plugin locally.
Frigade's HN maker post describes observing an app's existing requests, deriving typed endpoint recipes, and letting the app owner enable them as agent tools; changes can trigger recipe updates.
The template links a Gumloop agent to BasicOps through MCP so it can read task context, respond to mentions, and act within the workspace.
The author describes a Claude Code workflow that reads seven days of Substack performance, proposes topics, drafts Notes from voice files, and exports a scheduling CSV for review.
Jax describes a personal CRM built from Supabase, four MCP operations, and Markdown workflows. Claude enriches a supplied profile with Harmonic, attaches Granola notes, and supports contextual searches across contacts.
A self-hosted workflow parses a travel query with Gemini, obtains accommodation listings through MCP, and combines them with live Amadeus flight offers.