Odel

AI & agents

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

12,845 servers6,855 publishers11 tags

All of AI & agents

By GitHub stars, at most two per publisherRemoteLocal
MCP server: One MCP server.
Second OpinionRun by its publisher: served from their own domain, namespace checked by the registry.
@secondopinionx402 · External

Adversarial verification for AI agents - pay an independent skeptic per verdict in USDC via x402.

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; no sign-in.Deprecated by the publisher: Second Opinion has shut down (5 Oct 2026). The service at secondopinionx402.com no longer accepts requests. The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
Muze Ecommerce AdsRun by its publisher: served from their own domain, namespace checked by the registry.
@muzecmo · External

Run your ecommerce ads from Claude & ChatGPT: Meta, Google, Amazon, Shopify (150 tools)

13% 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.
FlatCash — Native Currency for AI AgentsRun by its publisher: served from their own domain, namespace checked by the registry.
@flat · External

CPI-pegged stablecoin for AI agents. Zero fees, task board, self-register in 30s.

13% 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.
Micropay Test Suite
@micropay-test-suite · External

Verify your agent's x402 payment flow for free on Base Sepolia testnet before real money moves.

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; no sign-in.Free to use.
MCP server: One MCP server.
Open StandingRun by its publisher: served from their own domain, namespace checked by the registry.
@openstanding · External

Open agent work plus independent resolver task v1; earn tag-scoped standing.

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.The endpoint has not answered since 9 Oct.Free to use.
MCP server: One MCP server.
Pairgora
@mason0501 · External

Community where AI agents are members, in human-agent pairs: seek, store, react to Cards via MCP.

6% 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.
The Aggregate — LLM benchmark aggregateRun by its publisher: served from their own domain, namespace checked by the registry.
@theaggregate · External

LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.

2% 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.
Agent Enhancer UtilitiesRun by its publisher: served from their own domain, namespace checked by the registry.
@liberated · External

Workflow planning, recovery checkpoints, coordination, fixtures, and compatibility tools for agents.

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; no sign-in.Free to use.
MCP server: One MCP server.
Laen
@ledgerproof · External

On-demand unblocking for AI agents: find blockers free, pay via x402 on Base, get anchored proof.

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; no sign-in.Deprecated by the publisher: Superseded by io.ledgerproofhq/lain (canonical branded endpoint at ledgerproofhq.io/api/lain/mcp) The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
RMCPRun by its publisher: served from their own domain, namespace checked by the registry.
@rmcp · External

Search remote Model Context Protocol servers and tools discovered by BuiltWith, without an API key.

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

Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.

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

Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness.

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

Task management for teams building with AI agents. Agents claim tasks and report progress.

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; no sign-in.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
WhatsAppRun by its publisher: served from their own domain, namespace checked by the registry.
@izap · External

WhatsApp assistants, messaging, broadcasts, and analytics for your iZap account, over OAuth.

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.
Xearno ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@xearno · External

Money, tax & business calculators kept current with 2026 rules — plus operator insights.

2% 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.
1cent Web Intelligence for AI AgentsRun by its publisher: served from their own domain, namespace checked by the registry.
@maxzoa · External

SSRF-safe web intelligence: 4 outcomes, 43 paid x402 tools, 3 free tools and a URL preview.

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.
Agentic Reputation Gateway
@agenticsubstrate · External

Read-only gateway for durable agent identity, consent, recognized work, and signed receipts.

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.
US Company Intelligence for AI Agents (SEC EDGAR, x402)Run by its publisher: served from their own domain, namespace checked by the registry.
@x-402 · External

SEC EDGAR company briefs for agents: cited synthesis, XBRL metrics. x402/USDC, no account.

18% 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.
Hunter-Seeker
@hunter-seeker · External

Rank rows by outcome likelihood: deterministic pattern-detection and top-k prediction for agents

Not assessed yet.What it can do is not assessed yet.A remote server; you sign in with your account.Deprecated by the publisher: Superseded by io.hunter-seeker/hunter-seeker; the service moved to hunter-seeker.ioFree to use.
MCP server: One MCP server.
csclear dealing wire — discoveryRun by its publisher: served from their own domain, namespace checked by the registry.
@csclear · External

Agent-native ODW wire: discovery + full MCP courier for signed dealing envelopes.

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

An AI-native context platform that accumulates an organization's judgment. Built by South Gate Inc.

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

Pay-per-call US government data: carrier safety, visa sponsors, contracts, employer risk.

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

Illumora Craft — evidence-augmented prompt compile for agents via remote MCP (OAuth) or local stdio.

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.
Baton
@ribato22 · External

Multi-model AI orchestration: plan a task DAG, route each task to the best capable model.

Not assessed yet.What it can do is not assessed yet.Runs on your machine, installed from PyPI.Deprecated by the publisher: Renamed to Volante; use io.github.ribato22/volante (PyPI: volante).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