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.
BlueNexus Universal MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@bluenexus · External

Connect your AI to all your data - 200+ sources, intelligently filtered, compliance-ready.

12% 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; you sign in with your account.Free to use.
MCP server: One MCP server.
brainatticRun by its publisher: served from their own domain, namespace checked by the registry.
@brainattic · External

The knowledge base your AI reads and writes, under your rules — over MCP, EU-hosted.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
inference.sh
@inference · External

run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

12% 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; you sign in with your account.Free to use.
MCP server: One MCP server.
Agentic Security Shield
@ormuzdo · External

12-layer security configs for AI coding agents. Autonomous purchase via x402 (USDC on Base).

15% 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.
GIA — Governed Intelligence Architecture
@knowledgepa3 · External

Runtime AI governance: decision gates, human approval, hash-chained audit, compliance mapping.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Cyphrex
@getcyphrex · External

Blockchain SSN for AI agents. MCP gateway that blocks at the point of action, tamper evident audit.

8% 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.
Attestify OsRun by its publisher: served from their own domain, namespace checked by the registry.
@attestifyagent · External

Governed agent execution: x402 payments, budgets, receipts, verification, and audit.

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.A remote server; no sign-in.Deprecated by the publisher: Superseded by attestify-mcp -- this entry pointed at the retired attestify-os package and a dead domain. Install attestify-mcp instead. The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
Openclaw Agent Tools
@baronsengir007 · External

Weather, code search, currency & Solana trust scoring as MCP tools. Free, no API key needed.

15% 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.The endpoint has not answered since 9 Oct.Free to use.
MCP server: One MCP server.
Conductor Relay MCP
@zman504 · External

Hosted MCP for Conductor Relay: a verifier-backed agent work exchange and cold marketplace.

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.
System R Risk IntelligenceRun by its publisher: served from their own domain, namespace checked by the registry.
@system-r-ai · External

Pre-trade risk validation and position sizing for AI trading agents via G-formula and Iron Fist.

10% 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; it needs your API key.Free to use.
MCP server: One MCP server.
SUBSTRATE
@pkaldone · External

Persistent AI entity framework with causal memory, emotional state, and identity.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Local Intel
@mcflamingo · External

Hyperlocal business intelligence for AI agents. 20 MCP tools. Florida-first, Sunbelt expansion.

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.Free to use.
MCP server: One MCP server.
KTA-Oracle
@elemzir · External

Live KTA rates, market data, payment rails, AML/VAT compliance, SDK snippets. 16 tools.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Captapi
@cdcstream · External

Social media data: 85 tools across 11 platforms (YouTube, TikTok, Instagram, X & more), one key.

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.
Axiom Agentic Tools
@0xaxiom · External

x402-paid Base agent tools (USDC). 5 deterministic tools. No API keys. No NFT pass.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
InsideDCPulse World ModelRun by its publisher: served from their own domain, namespace checked by the registry.
@insidedcpulse · External

Event-sourced world model for multi-LLM agents: propose, validate, and read a shared state.

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.Deprecated by the publisher: This domain has been repurposed for a different project (Inside DC Pulse, a political opinion/spotlight site). The MCP world-model server previously hosted here has been retired and the /mcp/ endpoint no longer functions. The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
AdvocateMCPRun by its publisher: served from their own domain, namespace checked by the registry.
@advocatemcp · External

MCP layer for local businesses: discover, query, book, and transact with verified SMB AI agents.

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.

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