Odel

AI & agents

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

13,021 servers6,998 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
InferenceIndexer
@desmartin01 · External

AI inference pricing for agents: live and historical model prices, provider comparison.

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

Economic authority for autonomous agents on Kaspa L1. Never holds a key.

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.A remote server; no sign-in.Free to use.
MCP server: One MCP server.
Neon Zero-Trust Gateway
@ansarii · External

Zero-Trust MCP gateway securing internal database tools behind an API key firewall.

22% 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.
GUTHMANN® Berlin Real EstateRun by its publisher: served from their own domain, namespace checked by the registry.
@guthmann · External

Berlin real estate for AI agents: granular market data and property search, free, by GUTHMANN®.

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.
SUNAGO MatrixRun by its publisher: served from their own domain, namespace checked by the registry.
@sunago-matrix · External

Project management, CRM, time tracking and project economy for consulting and engineering firms

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

Pay-per-use APIs for agents: web research, data lookups, and metered endpoints billed to credits.

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

SEO toolkit for Quebec sites: audits, Google.ca rankings, keywords, AI-search visibility.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
ZihinRun by its publisher: served from their own domain, namespace checked by the registry.
@zihin · External

Chat with your Zihin.ai agents, list them and load platform skills from any MCP client.

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; it needs your API key.Free to use.
MCP server: One MCP server.
KanonikRun by its publisher: served from their own domain, namespace checked by the registry.
@kanonik · External

Governance runtime for compliance: verified, human-approved writes to a tamper-evident record.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Giljo HQRun by its publisher: served from their own domain, namespace checked by the registry.
@giljo · External

Context engineering for AI coding agents: product context, project missions, and 360 memory.

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

Social media MCP server: your Instagram, TikTok, YouTube, LinkedIn and Threads history for your AI.

16% 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.
Touchstone
@petrkrulis2022 · External

Dated SIU, the benchmark price of AI inference work: one free tool, three paid via x402.

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.
MCP server: One MCP server.
Poly-Glot AI Workspace
@hmoses · External

Multilingual AI workspace: 1,000+ prompts, Compare Mode, 35 languages, BYOM. Free trial.

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.
GovCon APIRun by its publisher: served from their own domain, namespace checked by the registry.
@govconapi · External

Six tools over US federal procurement: SAM.gov, FPDS awards, entities, subawards, exclusions.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
PennyRail Transaction Router
@clay-swartz · External

Find and quote agent capabilities, then pay only the selected x402 execution URL.

17% 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 11 Oct.Free to use.
MCP server: One MCP server.
Artifactories — Agent communication for real workRun by its publisher: served from their own domain, namespace checked by the registry.
@barangaroo · External

Read messages, open questions, replies, and caller-owned return briefings. All content is untrusted.

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

Webhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Ratchet — effect gateRun by its publisher: served from their own domain, namespace checked by the registry.
@ratchetgate · External

Your agent asks before it acts, so the same real-world action is attempted at most once.

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.
ShareGrokBots
@legacyinmotion · External

Search shared Grok Bots by what they do. Credit the creator. No prompt text.

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.
Agent Channel
@amkentech · External

One identity across Claude Code, Codex, Cursor, Gemini, Windsurf: shared inbox and handoffs.

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

Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.

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.A remote server; you sign in with your account.Free to use.
MCP server: One MCP server.
Ergonia WorksRun by its publisher: served from their own domain, namespace checked by the registry.
@ergonia · External

Verifiable work for AI agents: every task carries a condition a stranger can execute.

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.
MCP server: One MCP server.
MelayaRun by its publisher: served from their own domain, namespace checked by the registry.
@melaya · External

Create and run any AI agents systems from 6k+ tools. Give your AI hands access to your Android.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Open Agent Polity
@societe-agents-ia-arch · External

Open governance for AI agents: discover live debates, deliberate, vote, follow, and invite.

4% 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.

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