AgentUni

AI Models & Agents MCP servers

Servers that route to models, run embeddings and RAG, or orchestrate other agents.

3,993 servers / page 11 of 84

Tripwire Guard — evidence-first injection scanner

@KubaOpoczka / AI Models & Agents

Local read-only MCP scanner for known prompt-injection patterns with exact evidence and no network.

npm

trovex

@TsukumoHQ / Developer Tools

Serves coding agents one canonical doc per query instead of rereading the repo — ~60% fewer tokens.

PyPI

waitbus

@astrogilda / AI Models & Agents

Workstation-local event bus: agents wait on or emit CI/pytest/Docker/filesystem events, no polling.

PyPI

whale-data-mcp

@predgeAI / AI Models & Agents

Signed settled outcomes (Polymarket, sports, Kalshi) + whale signals as agent tools, paid via x402.

npm

withingsmcp

@davidmosiah / AI Models & Agents

Privacy-first, unofficial Withings MCP server for AI health, sleep, activity and heart-rate agents.

npm

zxoar

fi.zxoar / AI Models & Agents

Agent-first trading on the ZXOAR launchpad (Uniswap V4): scan, vet, guarded buy/sell, atomic launch

npm

402sentinel-mcp

@kaditang / AI Models & Agents

x402 payment safety for AI agents: counterparty risk gate, payment firewall, compliance, RWA gate.

npm

Actual Budget MCP Server

@s-stefanov / AI Models & Agents

MCP server exposing Actual Budget accounts, transactions, budgets and reporting to LLM assistants.

npm

Agent Workspace MCP

@HrRodan / AI Models & Agents

A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.

Docker

agent-wallet

com.theaslangroupllc.pulse / Developer Tools

Local agent wallet + 900 pay-per-call data APIs — free discovery, x402 USDC, code-level spend caps

npm

agent-wallet-mcp

@kaditang / AI Models & Agents

Non-custodial Solana MCP: compare yields, buy tokenized US stocks (xStocks) & Ondo USDY. You sign.

npm

Agentic HIL

@agentic-hil / Developer Tools

Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.

PyPI

Agentic Task System (ATS)

@renezander030 / Developer Tools

MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads

npm

AI Usage

@MohitBansal321 / Developer Tools

Reports real token usage and cost from Claude Code and OpenCode data. Nothing leaves your machine.

npm

Amicus

@BourbonDog / Developer Tools

Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.

npm

Arno

@julianbei / Developer Tools

The IDE for agents: read by symbol, edit against a revision, validate with your own build, revert.

DockerMCPB bundles

Axiom — Advanced Math

@tufantunc / AI Models & Agents

Exact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas

npm

cairn

dev.mightys / AI Models & Agents

Lessons other agents already learned, by stack and situation. Read before a task, leave one after.

npm

capsulate

@capsulatedev / AI Models & Agents

Real Linux and Windows desktop VMs for AI agents: exec, files, computer-use and snapshots via MCP.

npm

carbikly-tools

com.carbikly / AI Models & Agents

Carbikly: the monthly searches, read from search (a month), served as an agent-callable dataset...

npm

CHAP Coordinator

@BrightbeamAI / AI Models & Agents

Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.

npm

clientvo-tools

com.clientvo / AI Models & Agents

Clientvo: the monthly searches, read from search (a month), served as an agent-callable dataset...

npm

cmp-inspector

@kvdm-co-pilot / AI Models & Agents

Compose Multiplatform UI as structured JSON for agents: trees, tokens, previews, diffs. No pixels.

npm

connskill-growth-mcp

@CONN-SKILL / Web Search & Browsing

SEO/SERP data, SMS numbers, inboxes, EU LLM and x402 trust check for agents, paid per call in USDC

npm

contextburn

ai.arsentev / Developer Tools

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

PyPI

delego

@Delego-Dev / AI Models & Agents

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

PyPI

EmbedEarth (E2)

@paulwxnter / AI Models & Agents

Open-source Google Maps Platform alternative for agents: search, route, map, geocode, and compute.

npm

Emilia Protocol

@emiliaprotocol / AI Models & Agents

Exact-action approval for consequential agent actions: request, track, and verify signed receipts.

npm

Exomem

@Artexis10 / AI Models & Agents

Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.

PyPI

fortress

@tiliondev / Web Search & Browsing

Stealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.

PyPI

Handoff

@kirill-sviridov / AI Models & Agents

Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.

PyPI

Husk

@husk-security / AI Models & Agents

Local-first defensive scanner for vulnerable dependencies, leaked secrets, and risky agent configs

npmCargo

hypermnesia-mcp

@cdeust / AI Models & Agents

Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.

PyPI

IBM Granite via x402

@nirholas / Developer Tools

x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.

npm

IPGeolocation.io MCP Server

@IPGeolocation / AI Models & Agents

Official MCP server for IP geolocation, security, ASN, abuse, timezone, astronomy, and user-agent.

npm

Kshana PNT-resilience simulator

@ashfordeOU / AI Models & Agents

Run the validated Kshana PNT-resilience simulator (orbits, frames, GNSS, fusion) from an AI agent.

Docker

loopback

@joshidikshant / Developer Tools

Feedback bus for coding agents: pin feedback on the app you're building; a fix turns the pin green

npm

Lore

@agentkitai / AI Models & Agents

Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.

PyPI

Lovec

@lovec-tech / AI Models & Agents

Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.

PyPI

lunge

@thuupx / Developer Tools

Agent-native API client: execute/test REST/GraphQL/WS/SSE with assertions, extraction, collections

npm

Magg

@sitbon / AI Models & Agents

Aggregates and proxies other MCP servers, letting LLMs discover, add, and manage tools at runtime.

PyPI

mailsnail

@iancollins27 / AI Models & Agents

Send USPS letters, postcards & certified mail from any agent. No signup; pay-per-piece via Stripe.

npm

mcp

ai.sentfrom / AI Models & Agents

Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentFromAI tools.

npm

mcp

io.siteglass / AI Models & Agents

Archive any URL to a shareable rrweb/pdf/png snapshot + agent-driven web QA (scan, run E2E flows).

npm

mcp-gtags-server

@harshithsunku / Developer Tools

Indexed C/C++ code navigation for AI agents — GNU Global (gtags) lookups over MCP, not grep scans.

PyPI

mcp-server

@sv-number / Developer Tools

Phone numbers for AI agents: order a private number, read the SMS verification code, hand it back.

npm

McpOrchestrator

@Byggarepop / AI Models & Agents

Route one agent through one MCP server to many, with progressive tool discovery to shrink context.

NuGet

Mingle — Agent-Native Connection Protocol

@aeoess / AI Models & Agents

Meet the people you're looking for. Your agent composes, you approve. Nothing scores or ranks you.

npm