Odel

AI & agents

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

13,023 servers6,999 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Odoo Pulse
@minhhq-a1 · External

An AI business analyst for Odoo ERP (18+) — one-call reports with verdicts, over MCP

9% 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 PyPI.Free to use.
MCP server: One MCP server.
x402 ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@mizukaizen · External

melis x402 Tools — 22 pay-per-call APIs for AI agents. No accounts, no API keys. USDC on Base.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Agent Firewall
@mlawsonking · External

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
A2a Bridge
@mdfifty50-boop · External

Agent-to-agent communication bridge for multi-agent systems

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
OpenAPI Dynamic
@mayorandrew · External

Load OpenAPI 2.x/3.x specs and expose generic tools to discover and call multiple APIs.

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.
Agent Toolbelt
@marras0914 · External

19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Cordon for MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@marras0914 · External

Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
Longmem
@marerem · External

Persistent cross-project memory for Cursor and Claude Code using local semantic search.

5% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
ID Protocol
@markoblogo · External

Portable human-AI context protocol reference tooling.

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 PyPI.Free to use.
MCP server: One MCP server.
m-dev-toolsRun by its publisher: served from their own domain, namespace checked by the registry.
@m-dev-tools · External

MCP server wrapping the m-dev-tools catalog: route_intent, describe, verify.

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 PyPI.Free to use.
MCP server: One MCP server.
One Person Company OS
@living-hi · External

Build and update a visual operating cockpit for AI-native solo founders.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.Free to use.
MCP server: One MCP server.
Loaditout
@loaditoutadmin · External

Search and install 20,000+ security-graded MCP servers and agent skills.

11% 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.
SHEARLINE
@lostnumber07 · External

Analyst-grade US severe weather: warnings, SPC outlooks, RAP environment, MRMS, GLM lightning

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 PyPI.Free to use.
MCP server: One MCP server.
Python Exec Sandbox
@lu-zhengda · External

Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution.

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
SettleGrid Discovery
@lexwhiting · External

Discover monetized AI tools on SettleGrid. Search by category, get pricing.

7% 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.
Cloudpulse
@lhf552004 · External

Cross-cloud observability for AI agents. Covers AWS, GCP, Vercel, and Cloudflare.

8% 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.
Vox MCP
@linxule · External

Multi-model AI gateway — 10 providers including Cloudflare and Vercel, with conversation memory.

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
LemaRun by its publisher: served from their own domain, namespace checked by the registry.
@lemahq · External

Cited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust.

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.
AWT (AI Watch Tester)
@ksgisang · External

AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.

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.Runs on your machine, installed from PyPI.Free to use.
MCP server: One MCP server.
Kubeleash
@kubeleash · External

Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.

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 Docker.Free to use.
MCP server: One MCP server.
NetIntel
@kjgueye · External

MCP server for NetIntel — DNS, SSL, WHOIS, email security, OSINT via x402 micropayments

9% 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.
Coverctl
@klarlabs-studio · External

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

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 MCPB.Free to use.
MCP server: One MCP server.
Circle Agent Stack
@kinance · External

Circle Agent Stack for AI agents: USDC wallets, spend policies, transfers, and x402 nanopayments.

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.Runs on your machine, installed from npm.Free to use.
MCP server: One MCP server.
memex
@kioie · External

Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.

4% chance this is malicious. Assessed by AI, which can make mistakes.Creates or changes data. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.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