Loading…
MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.
io.github.MNKIAgentOS/mnki-mcp is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 73/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding io.github.MNKIAgentOS/mnki-mcp to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
npx -y mnki-mcp@0.3.0Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-09-20T08:44:17.690278Z",
"publishedAt": "2026-09-20T08:44:17.690278Z",
"statusChangedAt": "2026-09-20T08:44:17.690278Z"
}
},
"server": {
"name": "io.github.MNKIAgentOS/mnki-mcp",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
"version": "0.3.0",
"packages": [
{
"version": "0.3.0",
"transport": {
"type": "stdio"
},
"identifier": "mnki-mcp",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"packageArguments": [
{
"name": "--agent",
"type": "named",
"valueHint": "invoice-agent",
"isRequired": true,
"description": "Agent identity the tool calls run under (create one in the console or with `mnki identity create`)."
},
{
"name": "--server",
"type": "named",
"valueHint": "github",
"description": "Name of the protected server, used in the ledger and the shadow log."
},
{
"name": "--mode",
"type": "named",
"default": "observe",
"description": "observe (default: log only), warn, require_approval or enforce."
},
{
"name": "--upstream",
"type": "named",
"valueHint": "-- npx -y @modelcontextprotocol/server-github",
"description": "The real MCP server to launch, after `--`: e.g. `-- npx -y @modelcontextprotocol/server-github`."
},
{
"name": "--upstream-url",
"type": "named",
"valueHint": "https://mcp.example.com/mcp",
"description": "Alternative to --upstream: a Streamable HTTP MCP server URL; add `--upstream-header k=v` for its auth."
}
],
"environmentVariables": [
{
"name": "MNKI_API_KEY",
"isSecret": true,
"isRequired": true,
"description": "Agent Trust API key with the verify scope (console → Settings → API keys)."
},
{
"name": "MNKI_URL",
"default": "https://mnki.com",
"description": "Console base URL; https://mnki.com unless self-hosted."
}
]
}
],
"repository": {
"url": "https://github.com/MNKIAgentOS/agent-trust",
"source": "github",
"subfolder": "packages/mcp"
},
"websiteUrl": "https://mnki.com/docs/integrations",
"description": "MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs."
}
}