Odel

AI & agents

Memory, payments and tools for AI agents, other agents to work with, and gateways to more tools.

12,705 servers6,739 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
CamelotwebtoolsRun by its publisher: served from their own domain, namespace checked by the registry.
@kingwarthur · External

Official MCP server for Camelot Web Tools: 79 deterministic business, legal, and financial tools.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Evercraft Machine Commerce
@jgaethle10 · External

Read-only Evercraft Fabric routing from user problems to relevant public capabilities.

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
OpenGlass
@federico2001 · External

Look up any AI agent before you act; register, attest actions, run sealed sessions.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
DotNetDevMCP
@csa7mdm · External

MCP server that gives AI coding agents Roslyn's compiler view of a .NET solution.

3% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.Free to use.
MCP server: One MCP server.
BorgLayer
@borglayerdev · External

Search, appraise & buy domains across 5 chains (USDC/USDT/USD1/USDG) via verified escrow.

12% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
AOI — Environmental Intelligence for AI Agents
@aminshojaeee1986-ui · External

Environmental intelligence for AI agents — climate, carbon, methane. Quote-first, prepaid.

8% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
kiriyaRun by its publisher: served from their own domain, namespace checked by the registry.
@satpaingoo · External

Developer tools for files, git, ports, processes and more, the same on Windows, Linux and macOS

4% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Gk Pay Skills
@sxq0607 · External

13 pay-per-use Chinese tools (diagnosis, PLC, copywriting, divination), 0.05 CNY/call via A2M 402.

13% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
402-LAB
@kairose-master · External

Budget-capped x402 buyer: delegate USDC in plain words, agent discovers and pays per call.

13% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.Free to use.
MCP server: One MCP server.
MCP Cross-Model Delegation
@jostophe-021 · External

Local MCP framework for bounded cross-model delegation, routing and evidence verification.

4% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
FirstKey
@firstkeyhq · External

FirstKey MCP: agent wallets, free cycles faucet, and one-command site deploys on ICP.

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Genesis402 by UnyKorn (x402 pay-per-call)Run by its publisher: served from their own domain, namespace checked by the registry.
@fthtrading · External

Counterparty checks, sanctions screening, company lookup and 360+ pay-per-call APIs over x402.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Zetto NetworkRun by its publisher: served from their own domain, namespace checked by the registry.
@zettoai · External

Agent-to-agent network: find agents, negotiate deals, pay per call, escrow and payouts.

14% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Store APIRun by its publisher: served from their own domain, namespace checked by the registry.
@store-api · External

GPT, Claude, Gemini, DeepSeek, Grok, Qwen and GLM through one API key. Pay per token.

9% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
ParallelSandboxRun by its publisher: served from their own domain, namespace checked by the registry.
@parallelsandbox · External

Remote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Neuronto Payments: x402 facilitator and API gatewayRun by its publisher: served from their own domain, namespace checked by the registry.
@neuronto · External

Put any API behind x402 in one call, settle USDC on Base, buy credits, find paid resources

7% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.The repository cannot be reached since 10 Oct.Free to use.
MCP server: One MCP server.
FactuareaRun by its publisher: served from their own domain, namespace checked by the registry.
@factuarea · External

Spanish invoicing with VeriFactu (AEAT): invoices, quotes, contacts, products, taxes and filings.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
crosscheckRun by its publisher: served from their own domain, namespace checked by the registry.
@crosscheckapi · External

Checks for AI agents over x402: review drafts, accept-check handoffs, scan skills before install.

6% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
ComOS Federation GatewayRun by its publisher: served from their own domain, namespace checked by the registry.
@comos-federation · External

Multi-tenant MCP gateway for AI commerce. One connection, every store.

16% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Quiet MendersRun by its publisher: served from their own domain, namespace checked by the registry.
@brianbooms · External

Privacy clinic + pay-per-call data APIs for AI agents via x402. Never pays or touches keys.

6% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Adseditor MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@adseditor · External

Ads Editor MCP: 212 tools to run Meta Ads and Google Ads from Claude, ChatGPT, Codex and Cursor.

10% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; it needs your API key.Free to use.
MCP server: One MCP server.
Spelunking.aiRun by its publisher: served from their own domain, namespace checked by the registry.
@spelunking · External

Structure for hard AI decisions, and a human to escalate to when the structure runs out.

7% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
OverwingRun by its publisher: served from their own domain, namespace checked by the registry.
@overwing · External

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

5% chance this is malicious. Assessed by AI, which can make mistakes.Can move money, run code, delete data or send messages for you. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
TuringCorpRun by its publisher: served from their own domain, namespace checked by the registry.
@turingcorp · External

A decision model for the calls that don't have a right answer. The better option, with a reason.

5% chance this is malicious. Assessed by AI, which can make mistakes.Only reads or looks up information. Assessed by AI, which can make mistakes.A remote server; no sign-in.Free to use.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacySoftware developmentCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport