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.
-
@agentutil/think-mcpgithub.com/craig-whitfield/think-mcpupdated this year
MCP server — intent security pre-flight checks for autonomous AI agents
npm MIT -
think-mcpgithub.com/craig-whitfield/think-mcpupdated this year
MCP server for intent security pre-flight checks for autonomous AI agents
-
Vigilancegithub.com/B-A-M-N/Vigilanceupdated this year
A security minded , realtime AI Intent Observability MCP providing intent tagging and visual mirroring of AI attention to see what context the AI is looking at. Made for visual and coding workflows.
NOASSERTION ★ 1 -
mdbpgithub.com/dorukyelken/mdbpupdated this year
Model Database Protocol — intent-based, secure database access for LLMs with schema validation, policy engine, data masking, and MCP server support
pypi MIT -
Model-Database-Protocolgithub.com/DorukYelken/Model-Database-Protocolupdated this year
Model Database Protocol — intent-based, secure database access for LLMs with schema validation, policy engine, data masking, and MCP server support
★ 8 -
gocreative-wedge-mcpupdated this year
Fiat-billed MCP server for AI agents: OFAC/PEP/watchlist sanctions screening, EU consolidated (FSF) sanctions, KYB, company + people enrichment, prospect/vendor/onboard 360 diligence bundles, intent-based lead search, EU VAT (VIES) validation, SEC XBRL company financials, FDA drug-recall screen, securities-reference-360 (ISIN -> listings + FIGIs), LEI -> issued ISINs, domain trust score, and GLEIF fund relationships. Pay with a card — no crypto wallet. Free demo tools, no key.
pypi MIT -
phishcheckgithub.com/cognis-digital/phishcheckupdated this year
Score URLs/emails for phishing signals (lookalike, auth, intent)
NOASSERTION -
sigsleuthgithub.com/cognis-digital/sigsleuthupdated this year
Decodes raw calldata and EIP-712 typed-data into human-readable intent, flagging blind-signing and malicious permit/Permit2 payloads.
NOASSERTION -
@mseep/urlcheck-openclawgithub.com/cybrlab-ai/urlcheck-openclawupdated this year
URLCheck plugin for OpenClaw. Assess target URLs for potential threats and alignment with the user's browsing intent before agent navigation.
npm Apache-2.0