protogrid
Sign inAdd to your agent

Search / io.github.pcas-io/plexus

plexus

not classified

Typed on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP.

v0.1.2 · active · repository · descriptor JSON · versions

Not classified yet.The remote endpoints have not been probed successfully, or the listing has nothing to connect to.
Quality–not scored
Trust81of 100
Uptime, 30 days–
Latency p50–

Connect

8 clients · secrets stay placeholders

No connection block: no_connection.

Quality – / 100not scored

Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.

protocoln/a · weight 25
  • n/a
    protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorization100 · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • pass
    auth.secret_in_urlURL variables carry no secret
tool hygienen/a · weight 30
  • n/a
    tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool list unknown
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

Tool list unknown · checked 2026-10-19 15:48 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 81 / 100

provenance80
livenessn/a
freshness65
hygiene100

+repository +namespace-matches-repo ~liveness-unmeasured ~updated-175d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://{plexus_host}/mcp streamable-http · templatedunknownnot probed––––

Tools (0)

No tools observed. Tools appear once a credential-free probe can list them.

Schemas: list_tools.

Similar MCP servers

  • vector-knowledge-graph-mcpL0
    io.github.CSOAI-ORG/vector-knowledge-graph-mcp

    AI-powered vector knowledge graph MCP server for agents. Supports add node, add edge, semantic node

  • JunêL0
    io.github.Junemind/june-mcp

    Shared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions

  • knowingL0
    io.github.blackwell-systems/knowing

    Content-addressed code graph with 22 MCP tools for AI agents.

  • plurL0
    io.github.plur-ai/plur

    Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.

  • mcpL0
    ai.clawfetch/mcp

    Web intelligence for AI agents: fetch, render, extract, research. x402 micropayments, no API keys.

  • pulse8-ai-cortex-knowledge-vaultL0
    io.github.synpulse8-opensource/pulse8-ai-cortex-knowledge-vault

    Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.

Official server.json
{
  "name": "io.github.pcas-io/plexus",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://{plexus_host}/mcp",
      "type": "streamable-http",
      "variables": {
        "plexus_host": {
          "description": "Hostname of your self-hosted plexus instance, e.g. plexus.example.com. plexus is on-prem by design; there is no shared public instance."
        }
      }
    }
  ],
  "version": "0.1.2",
  "repository": {
    "url": "https://github.com/pcas-io/plexus",
    "source": "github"
  },
  "description": "Typed on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP."
}