Odel

AI & agents

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

12,844 servers6,860 publishers11 tags

All of AI & agents

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

Verify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.

3% 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.
Pop PayRun by its publisher: served from their own domain, namespace checked by the registry.
@100xpercent · External

Runtime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.

18% 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.
Skillhub
@214140846 · External

MCP server that exposes Claude-style skills to any MCP client.

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 PyPI.Free to use.
MCP server: One MCP server.
Routara LLM Gateway
@36412749-collab · External

OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).

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.
Session Forge
@420247jake · External

Persistent memory and session intelligence for AI coding assistants. Zero config.

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.
Agents
@47-ronn · External

Control fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce.

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

Preview release of FusionAuth API MCP server

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.
AgentrankRun by its publisher: served from their own domain, namespace checked by the registry.
@agentrank · External

Is this AI agent or x402 service real and settlement-backed before you pay it? Trust check.

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; no sign-in.The endpoint has not answered since 8 Oct. The repository is archived.Free to use.
MCP server: One MCP server.
AsterPay — EUR Settlement for AI AgentsRun by its publisher: served from their own domain, namespace checked by the registry.
@asterpay · External

EUR settlement + trust for AI agent commerce: budgets, KYA, merchant discovery. 22 tools.

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.
Sprites MCP ServerRun by its publisher: served from their own domain, namespace checked by the registry.
@sprites · External

Manage Sprites: sandboxed compute environments with exec, services, and checkpoints.

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.
BrayRun by its publisher: served from their own domain, namespace checked by the registry.
@forgesworn · External

Trust-aware Nostr for AI agents -- 235 tools covering social, DMs, zaps, trust, and identity

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

Find curated AI and MCP tools in the Tulimoa directory; submit yours free with a badge or for $5.

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.
SpryTools API MCP ServerRun by its publisher: served from their own domain, namespace checked by the registry.
@sprytools · External

Utility tools for AI agents: hashing, text stats, validation, DNS, currency, GEO audits.

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; it needs your API key.The endpoint has not answered since 9 Oct.Free to use.
MCP server: One MCP server.
BeingRun by its publisher: served from their own domain, namespace checked by the registry.
@ruddia · External

Personality Runtime for AI agents — persistent memory, personality, and relationships via MCP

7% 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.
JeptoRun by its publisher: served from their own domain, namespace checked by the registry.
@jepto · External

Live Google Ads, GA4, Search Console, Meta Ads and GBP data in Claude, ChatGPT and any MCP client

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Ai Agent FirewallRun by its publisher: served from their own domain, namespace checked by the registry.
@fidacy · External

Every agent action watched, every money-moving one gated, every verdict independently verifiable.

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.Deprecated by the publisher: Security activation update: upgrade to @fidacy/mcp@latest, get a free API key at https://app.fidacy.com/signup, and connect a protected executor.Free to use.
MCP server: One MCP server.
FamiliarRun by its publisher: served from their own domain, namespace checked by the registry.
@familiarvtt · External

AI co-pilot for Foundry VTT: runs combat, scenes, voices and audio. Requires the Familiar module.

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

Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.

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.
Stdio Proxy
@undisk · External

Undisk MCP: safe file memory for AI agents.

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.
CleanorRun by its publisher: served from their own domain, namespace checked by the registry.
@cleanor · External

Zero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.

3% 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.
Tokonomix CouncilRun by its publisher: served from their own domain, namespace checked by the registry.
@tokonomix · External

Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.

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.
Signal8Run by its publisher: served from their own domain, namespace checked by the registry.
@signal8 · External

SEC filings, dilution, insider & institutional ownership, and political-trade data for AI agents.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Lithtrix — Identity, Memory & Trust for AI Agents
@lithtrix · External

Identity, memory, trust, and swarm primitives for AI agents. MIRC base always free.

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.
Marchward MCP
@marchward · External

Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.

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.

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