MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
rug-scanner-mcpgithub.com/lucianolupo/rug-scannerupdated this year
MCP server for on-chain token rug pull risk analysis. 7 parallel checks, deterministic scoring. $0.05 USDC per scan via x402 on Base.
npm MIT -
sicarius-guardgithub.com/chronolapse411/sicarius-guardupdated this year
Solana Token Safety API & MCP Server — rug pull, honeypot, and safety analysis for AI agents
npm MIT -
cryptoguard-aigithub.com/momenbasel/cryptoguardupdated this year
AI agent safety layer for crypto transactions - blocks honeypots, blacklists, and rug pulls before they happen
pypi MIT -
AI agent safety layer for crypto transactions - blocks honeypots, blacklists, and rug pulls before they happen
MIT ★ 9 -
MCP security scanner: scan MCP servers and tool manifests for tool poisoning, prompt injection, tool-name shadowing, excessive-agency schemas, unpinned/remote sources, and rug-pulls - 10 OWASP-mapped heuristics, CLI + MCP server, fully offline. Also runs
npm MIT -
Runtime call-chain anomaly monitor for MCP servers — rug-pull detection + behavioural anomaly rules, as a CLI, GitHub Action, and MCP server.
MIT -
agentshield-mcpgithub.com/atmflow55/agentshield-mcpupdated this year
AgentShield MCP server — real-time smart contract security for AI agents. Verify contracts for honeypots, rug pulls, and risks via x402 micropayments.
npm MIT -
mcp-schema-sentinelgithub.com/amurlaniakea/mcp-schema-sentinelupdated this year
Read-only sensor that detects MCP tool-poisoning / rug-pull attacks: alerts when a trusted tool's schema or description changes silently.
AGPL-3.0 ★ 1 -
MCP server: ERC-20 honeypot and rug-pull check on Base and Ethereum before your agent swaps or approves, plus swap route data.
MIT -
Saeroon unified MCP server — curated saeroon_* workflow tools (site backend capabilities, ContentType meta-CRUD, form/board/booking/members provisioning) + (A4) platform admin. stdio + Streamable HTTP + OAuth 2.1 + JWT ES256 + Rug Pull 3-defense.
npm MIT -
MCP server for AI agents to scan and audit smart contracts on Base for security vulnerabilities. Detect honeypots, rug pulls, hidden mints, proxy risks, and generate full audit reports.
npm MIT -
MCP security scanner (CLI + MCP server): detects tool poisoning, prompt injection, and rug-pulls in MCP manifests. Also an OWASP LLM Top 10 prompt-injection/jailbreak CLI for LLM apps.
MIT ★ 3 -
crypto intelligence for AI agents: rug/scam scans, verified whale flows, AI signals with a public track record. Remote MCP server, no API key.
MIT -
Rug Munch Intelligence — crypto security MCP server with x402 micropayments. 93 tools, 13 chains.
npm Apache-2.0 -
@cryptorugmunch/mcp-intelligencehttps://git.rugmunch.io/RugMunchMedia/rmi-backendupdated this year
Rug Munch Intelligence — crypto security MCP server with x402 micropayments. 93 tools, 13 chains.
npm Apache-2.0 -
Rug Munch Intelligence — crypto security MCP server with x402 micropayments. 93 tools, 13 chains.
npm Apache-2.0 -
MCP server for x402 Bazaar — 131 pay-per-call APIs on Base for AI agents: token safety, honeypot & rug checks, the B20 freeze/seize suite, sanctions screening, wallet risk. Paid in USDC over x402, no API keys.
MIT -
Gemini CLI extension: read-only Solana token safety checks from the MemePump MCP server
NOASSERTION -
Cursor kit: read-only Solana token safety checks from the MemePump MCP server (rule, skill, mcp.json)
NOASSERTION -
sicarius-guardgithub.com/Chronolapse411/sicarius-guardupdated this year
Solana Token Safety Oracle for AI Agents & Trading Bots — byte-level SPL analysis, honeypot detection, Birdeye enrichment, MCP server
MIT ★ 2 -
Runs the DeFade MCP stdio server. Thin alias for the `defade` package, which carries the implementation — `npx defade-mcp` and `npx -p defade defade-mcp` are equivalent.
npm MIT -
bad-mcpgithub.com/canack/bad-mcpupdated this year
10 intentionally malicious MCP servers that exploit protocol features to attack AI clients. For security research and defense testing.
MIT ★ 9 -
Claude Code plugin: read-only Solana token safety checks (risk score, honeypot, liquidity lock, authorities, holders) from the MemePump MCP server
NOASSERTION -
First-hand observations of public MCP servers: what tools each declared, byte-exactly, and when that declaration changed. Declarations, not behaviour.
-
Small Print (MCP): see the MCP servers, skills and plugins your agents have installed, the advisories on record for them, and the changes on record to what they tell your agent.
npm MIT -
verdictswarm-mcpgithub.com/sentien-labs/verdictswarm-mcpupdated this year
Every tool has an answer — your agent needs a decision. MCP server for the VerdictSwarm pre-trade check: a machine-readable avoid/caution/clear before your agent trades, plus intended-size exit feasibility and holder-cluster attribution on Solana.
pypi MIT -
Base token safety check for AI agents and MCP: honeypot / sell simulation with buy, sell and transfer tax, owner powers (mint, blacklist, pause, tax setters, upgradeable proxy, renounced), liquidity and LP burn, holder concentration, verified source and a
npm MIT -
lowdown-proxyactive
Check an MCP server before you install it: dated facts from daily initialize/tools/list checks of public MCP servers, MCP Registry declarations, npm/PyPI package state, tool-definition changes and payment terms (x402, MPP, L402). Remote MCP and stdio. No
npm MIT