Odel

Software development

Code, repositories, reviews, tests, debugging, databases and developer docs.

5,511 servers4,398 publishers15 tags

All of Software development

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

AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).

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.
Gonka Second Opinion (multi-model)
@bystray · External

A second opinion for AI agents: one prompt across several live Gonka models + roles, one call.

17% 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.
Ask262
@bendtherules · External

MCP server for understanding Javascript internals from ECMAScript specification.

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.The endpoint has not answered since 8 Oct.Free to use.
MCP server: One MCP server.
Meridian
@ajc3xc · External

Persistent memory, task coordination, and HITL queue for AI coding sessions.

18% 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.
Dockerfile Audit
@unbearabledev · External

Hadolint-grade Dockerfile audit — 19 checks: secrets, privileges, supply chain, hygiene.

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; it needs your API key.Free to use.
MCP server: One MCP server.
GitHub Actions Audit
@unbearabledev · External

GitHub Actions workflow security audit - 21 checks: pinning, permissions, secrets, injection.

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.
Vonage Documentation
@vonage · External

MCP server for Vonage API documentation, code snippets, tutorials, and troubleshooting.

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.
Dora
@saga-labs · External

Multi-model AI image and video generator. 14 models behind one OAuth-secured MCP endpoint.

9% 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.
PlainQuery | MCP DB Agent
@jarvis-27 · External

Query PostgreSQL databases in plain English — LLM-generated, safety-validated SQL.

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; it needs your API key.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
Mockmcp
@k-cupples · External

Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.

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; no sign-in.The endpoint has not answered since 10 Oct.Free to use.
MCP server: One MCP server.
Fixflow
@magneticdogson · External

Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.

15% 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.
Compuute MCP Security Scanner
@compuute · External

Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.

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

BuildPulse CI test analytics for AI agents — flaky tests, CI failures, flakiness, and code coverage.

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

Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for

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: Remote endpoint https://api.meok.ai/v1/a2a/agent-replay-debugger is not live: api.meok.ai has no public DNS answer (checked via 1.1.1.1, 2026-09-29). Deprecated by the publisher until a live endpoint exists. The PyPI package agent-replay-debugger-mcp still installs and runs locally over stdio. The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
Spec Compliance
@csoai-org · External

MCP Spec Compliance MCP — audits any MCP server.json against the official Model Context Protocol

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.Deprecated by the publisher: Remote endpoint https://api.meok.ai/v1/dev/mcp-spec-compliance is not live: api.meok.ai has no public DNS answer (checked via 1.1.1.1, 2026-09-29). Deprecated by the publisher until a live endpoint exists. The PyPI package mcp-spec-compliance-mcp still installs and runs locally over stdio. The endpoint has not answered since 1 Oct.Free to use.
MCP server: One MCP server.
Nordic Financial MCP
@aidatanordic · External

Semantic search over Nordic filings, press releases, macro data and electricity prices.

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.
Appcircle MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@appcircle · External

MCP server for Appcircle mobile CI/CD platform.

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

Send a coupling matrix, get zone classifications and optimal factorization strategy.

10% 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.
Foresea ForecastingRun by its publisher: served from their own domain, namespace checked by the registry.
@foresea · External

Forecast future events and scan prediction-market edges.

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.
Ink MCPRun by its publisher: served from their own domain, namespace checked by the registry.
@ml · External

Deploy and manage applications, databases, domains, and git repos

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.
Moddable Games ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@moddable · External

15 tools for chess variant analysis, hex map generation, and board game utilities

2% 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.
codeitallRun by its publisher: served from their own domain, namespace checked by the registry.
@codeitall · External

Behavioral oracle for Rust crate APIs: runtime behavior, yank/advisory, deprecation, sig search

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.The endpoint has not answered since 12 Oct.Free to use.
MCP server: One MCP server.
SipflowRun by its publisher: served from their own domain, namespace checked by the registry.
@sipflow · External

SIP/VoIP/telecom grounding for AI agents: vendor docs, RFCs, STIR/SHAKEN, traces, configs.

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

A personal RAG database you build from chat, so AI creates work that sounds like you.

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.

More topics

Sales & customersMarketing & advertisingShopping & e-commerceBusiness financePersonal finance & investingLegal & governmentSecurity & privacyAI & agentsCloud & IT operationsData & webWork & productivityCommunicationDocuments & writingDesign & mediaNews & informationScience & researchHealth & fitnessEducation & careersTravel & placesHome & propertyEntertainment & hobbiesIndustry & transport