AI Models & Agents MCP servers
Servers that route to models, run embeddings and RAG, or orchestrate other agents.
Tripwire Guard — evidence-first injection scanner
Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.
trovex
Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.
waitbus
Workstation-local event bus: agents wait on or emit CI/pytest/Docker/filesystem events, no polling.
whale-data-mcp
Signed settled outcomes (Polymarket, sports, Kalshi) + whale signals as agent tools, paid via x402.
withingsmcp
Privacy-first, unofficial Withings MCP server for AI health, sleep, activity and heart-rate agents.
zxoar
Agent-first trading on the ZXOAR launchpad (Uniswap V4): scan, vet, guarded buy/sell, atomic launch
402sentinel-mcp
x402 payment safety for AI agents: counterparty risk gate, payment firewall, compliance, RWA gate.
Actual Budget MCP Server
MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.
Agent Workspace MCP
A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
agent-wallet
Local agent wallet + 900 pay-per-call data APIs — free discovery, x402 USDC, code-level spend caps
agent-wallet-mcp
Non-custodial Solana MCP: compare yields, buy tokenized US stocks (xStocks) & Ondo USDY. You sign.
Agentic HIL
Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.
Agentic Task System (ATS)
MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads
AI Usage
Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.
Amicus
Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.
Arno
The IDE for agents: read by symbol, edit against a revision, validate with your own build, revert.
Axiom — Advanced Math
Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas
cairn
Lessons other agents already learned, by stack and situation. Read before a task, leave one after.
capsulate
Real Linux and Windows desktop VMs for AI agents: exec, files, computer-use and snapshots via MCP.
carbikly-tools
Carbikly: the monthly searches, read from search (a month), served as an agent-callable dataset...
CHAP Coordinator
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
clientvo-tools
Clientvo: the monthly searches, read from search (a month), served as an agent-callable dataset...
cmp-inspector
Compose Multiplatform UI as structured JSON for agents: trees, tokens, previews, diffs. No pixels.
connskill-growth-mcp
SEO/SERP data, SMS numbers, inboxes, EU LLM and x402 trust check for agents, paid per call in USDC
contextburn
Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.
delego
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
EmbedEarth (E2)
Open-source Google Maps Platform alternative for agents: search, route, map, geocode, and compute.
Emilia Protocol
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
Exomem
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
fortress
Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.
Handoff
Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
Husk
Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs
hypermnesia-mcp
Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.
IBM Granite via x402
x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.
IPGeolocation.io MCP Server
Official MCP server for IP geolocation, security, ASN, abuse, timezone, astronomy, and user-agent.
Kshana PNT-resilience simulator
Run the validated Kshana PNT-resilience simulator (orbits, frames, GNSS, fusion) from an AI agent.
loopback
Feedback bus for coding agents: pin feedback on the app you're building; a fix turns the pin green
Lore
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
Lovec
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
lunge
Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections
Magg
Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.
mailsnail
Send USPS letters, postcards & certified mail from any agent. No signup; pay-per-piece via Stripe.
mcp
Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentFromAI tools.
mcp
Archive any URL to a shareable rrweb/pdf/png snapshot + agent-driven web QA (scan, run E2E flows).
mcp-gtags-server
Indexed C/C++ code navigation for AI agents — GNU Global (gtags) lookups over MCP, not grep scans.
mcp-server
Phone numbers for AI agents: order a private number, read the SMS verification code, hand it back.
McpOrchestrator
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
Mingle — Agent-Native Connection Protocol
Meet the people you're looking for. Your agent composes, you approve. Nothing scores or ranks you.