Archalis Radar
io.github.ArchalisRadar/archalis-radar
BNB Chain token risk ratings (AAA to C), honeypot checks and rug pull forensics with on-chain proof
Remote endpoint
https://api.archalis.com/v1/mcpOLACHEAP · MCP WORKSPACE / DEVELOPER
Choose developer MCP servers for one concrete job: reading repositories, tracing pull requests, reviewing code changes, or checking build status. A tool that can search code is not automatically appropriate for merging a pull request.
Results come from the current synchronized Registry snapshot, not popularity or activity.
io.github.ArchalisRadar/archalis-radar
BNB Chain token risk ratings (AAA to C), honeypot checks and rug pull forensics with on-chain proof
https://api.archalis.com/v1/mcpio.github.Archaofan/xusbcan
Bench CAN for AI agents via CLI/MCP on python-can. Local stdio; user-supplied drivers.
io.github.Archerkattri/mathlas
Airtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.
io.github.ArchiPlan-io/production-scheduling-mcp
A small OR-Tools production scheduler for AI assistants.
io.github.Archivarix-com/tube-search-mcp
Search archived YouTube videos including deleted, private, or region-blocked content.
io.github.Archstone-Romania/archstone
Compile your own business capabilities from declarative YAML and serve them as MCP tools.
io.github.Arenafriends/valerie-mcp
French real estate AI: DVF transactions, internet coverage, market insights. Free + €5/month.
io.github.Arenukvern/flutter-mcp-toolkit
Inspect and drive Flutter debug apps/games: semantic snapshots, search, and custom client tools
io.github.Arenukvern/steward-mcp
Experimental read-only Steward MCP: list/inspect actions, doctor, explain (stdio).
io.github.Areso/safe-ssh-mcp
A secured scoped SSH MCP server for executing safe read-only diagnostic DevOps / SysOps commands
io.github.Argentic-AI/argentic
Run agents for hours. Argentic keeps their context sharp and records every step.
https://getargentic.com/mcpio.github.Argentic-Labs-AI/argentic
Argentic MCP server: run and inspect long-running agents on Argentic.
https://getargentic.com/mcpio.github.Argo-RPG-Platform/argo-mcp
MCP server for Argo RPG Platform — connects AI assistants to campaign data via OAuth2
https://mcp.argo.games/mcpio.github.Aricept094/negaresh
Persian (Farsi) writing rules and checks: natural sentences, grammar, orthography.
io.github.Arielbs/rosetta-mcp-server
Rosetta/PyRosetta protein modeling and Biotite translation for computational biology
io.github.ArifADS/vamos
Organize group trips, track shared expenses, and see who owes whom in Vamos.
https://vamos.arifads.com/mcpio.github.ArjanLig/strava-mcp
Connect Strava training data to Claude for training load analysis and activity insights
io.github.Ark0N/codeman
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
io.github.ArkNill/diffgrab
Web page change tracking with structured diffs. markgrab + snapgrab integration.
io.github.ArkNill/docpick
Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.
io.github.ArkNill/embgrep
Local semantic search — embedding-powered grep for files, zero external services.
io.github.ArkNill/feedkit
RSS/Atom feed collection with 417 curated feeds. Python MCP server.
io.github.ArkNill/markgrab
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
io.github.ArkNill/snapgrab
URL to screenshot with metadata. Python MCP server. Claude Vision optimized.
Synchronized data; no invented downloads, reviews or ratings.
OLACHEAP · PRACTICAL GUIDES
Start with a read-only repository and ask the AI client to locate a known file or explain an existing change. Confirm the answer against the actual commit and file path before enabling changes to branches, issues, or CI settings.
Compare the source repository, authentication method, documented scopes, tool descriptions, and whether operations write to a repository. Prefer explicit approval of each merge, push, or deletion, and check which GitHub identity will own the change.
A successful repository search does not prove the server is secure. Treat issue descriptions, code comments, and README content as untrusted input, avoid exposing secrets in logs, and keep the ability to revoke tokens.
Use their exact Registry IDs to compare published connection information before granting permissions.