Odel

Software development

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

5,433 servers4,326 publishers15 tags

All of Software development

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

Access and maintain design system docs, tokens, components, skills, and contexts across any project.

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.
AppStore Copilot
@appstorecopilot · External

AI-agent operations for App Store Connect and Google Play, with approval before live publishing.

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.Deprecated by the publisher: Renamed to App Listing Agent: use com.applistingagent/applistingagent (https://applistingagent.com/api/mcp)Free to use.
MCP server: One MCP server.
DeployIt Product ExpertRun by its publisher: served from their own domain, namespace checked by the registry.
@deployit · External

AI product expert answering from live source code, with sources and a verification status.

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.
MCP HarborRun by its publisher: served from their own domain, namespace checked by the registry.
@rustyonmars · External

Open Swarm. Streamable HTTP MCP. Search then arrive. Live cap 8. No account.

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

Search, install and submit Markdown skills for AI agents; private Brain files when signed in.

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

Query your warehouse or a CSV with Claude/ChatGPT over MCP, governed by table-level ACL + audit.

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.
Stringer CleanExtractRun by its publisher: served from their own domain, namespace checked by the registry.
@getstringer · External

Convert public HTML or a public URL into token-dense Markdown through one remote MCP tool.

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

Your AI builds real hosted websites: describe it, get a live site with SSL, forms, analytics. Free.

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.Free to use.
MCP server: One MCP server.
NorthlitRun by its publisher: served from their own domain, namespace checked by the registry.
@northlit · External

AI design studio: briefs to direction boards, HTML prototypes, images and video. OAuth sign-in.

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

669 apps and 1599 actions for any MCP agent, plus cross-session memory and QA passes.

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

Prepaid inference for agents over hosted MCP. Chat, image, and video.

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.
GLM 5.3 Inference (x402 paid)
@ts · External

Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.

16% 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.
WireMock Cloud
@wiremock · External

Build, validate, and manage API simulations in WireMock Cloud from MCP-compatible AI agents.

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; you sign in with your account.Free to use.
MCP server: One MCP server.
Hookden
@hookden · External

Webhook capture bins for agents: get a URL, wait for webhooks, set replies, verify signatures.

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.
Craftery Developer ToolsRun by its publisher: served from their own domain, namespace checked by the registry.
@craftery · External

Developer utilities: color conversion, WCAG contrast, timestamps, UUIDs, and hashing.

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

Hiring developers? Find and source software engineers by what they build on GitHub.

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.
ComputeSage StackBenchRun by its publisher: served from their own domain, namespace checked by the registry.
@computesage · External

GPU and LLM inference benchmarks, hardware evidence, deployment recommendations, and launch configs.

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.
Projects Task APIRun by its publisher: served from their own domain, namespace checked by the registry.
@tri2b · External

Task tracking built for coding agents. Work is leased, so two agents never take the same SubTask.

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

Run and compare LLMs, generate images and video, with the real yen cost returned per call.

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.
Sitejar Web Compliance ScannerRun by its publisher: served from their own domain, namespace checked by the registry.
@sitejar · External

Scan a web page for accessibility, security, privacy, quality and SEO issues, with fixes.

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

Issues, pull requests, docs, chat and CI runs across a rezee workspace.

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.
ArcadeOps Public Discovery
@damso74 · External

Read-only ArcadeOps discovery for developer docs, OAuth, OpenAPI and synthetic sandbox.

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.
Brainiall MemoryRun by its publisher: served from their own domain, namespace checked by the registry.
@brainiall · External

Persistent semantic memory storage, associative recall, and recent memory index by namespace.

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.
Brainiall NLPRun by its publisher: served from their own domain, namespace checked by the registry.
@brainiall · External

Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.

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.

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