protogrid
Sign inAdd to your agent

Search / io.github.donggyun112/keymem

keymem

L0· runs locally

Associative key-graph memory for LLM agents — recall by association, not vector similarity.

v0.17.0 · active · repository · descriptor JSON · versions

Runs on your machine: something must execute the package.Only local packages are published (npm, PyPI, OCI, …). The registry never executes them, so tools are unknown until you run it.
Quality–not scored
Trust87of 100
Packages1
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "keymem": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
claude mcp add keymem -- npx -y [email protected]
[mcp_servers.keymem]
command = "npx"
args = ["-y", "[email protected]"]

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "keymem": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "[email protected]"
      ],
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "keymem": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=keymem&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImtleW1lbUAwLjE3LjAiXX0%3D"
}
{
  "servers": {
    "keymem": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
{
  "mcpServers": {
    "keymem": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ]
    }
  }
}
extensions:
  "keymem":
    enabled: true
    name: "keymem"
    type: stdio
    cmd: "npx"
    args:
      - "-y"
      - "[email protected]"
    timeout: 300

This is a local package: the command runs on your machine.

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)
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
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
dependencies33 · weight 15
  • fail
    deps.known_vulns9 advisories to act on (malicious, or rated high or critical with a fix available): GHSA-23hp-3jrh-7fpw in [email protected] (indirect, fixed in 7.5.19), GHSA-34x7-hfp2-rc4v in [email protected] (indirect, fixed in 7.5.7), GHSA-83g3-92jg-28cx in [email protected] (indirect, fixed in 7.5.8), ...; 4 more of lower severity or without a fix
  • fail
    deps.mcp_sdk_version@modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
  • pass
    deps.resolvable[email protected] resolved: 179 packages

Tool list unknown · checked 2026-10-19 10:20 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 87 / 100

provenance80
livenessn/a
freshness85
hygiene100

+repository +namespace-matches-repo ~liveness-unmeasured ~updated-89d-ago

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

Dependencies

[email protected] npm178 dependencies, resolved · MCP SDK @modelcontextprotocol/sdk 1.30.1 · advisories checked 2026-10-19

advisoryseveritypackagefixed in
GHSA-23hp-3jrh-7fpwnode-tar: Decompression/parse DoS via unlimited inputcritical[email protected]indirectfixed in 7.5.19
GHSA-6qxp-vccf-f47hMCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP serverhigh@modelcontextprotocol/[email protected]MCP SDK, directfixed in 1.31.0
GHSA-34x7-hfp2-rc4vnode-tar Vulnerable to Arbitrary File Creation/Overwrite via Hardlink Path Traversalhigh[email protected]indirectfixed in 7.5.7
GHSA-83g3-92jg-28cxArbitrary File Read/Write via Hardlink Target Escape Through Symlink Chain in node-tar Extractionhigh[email protected]indirectfixed in 7.5.8
GHSA-8qq5-rm4j-mr97node-tar is Vulnerable to Arbitrary File Overwrite and Symlink Poisoning via Insufficient Path Sanitizationhigh[email protected]indirectfixed in 7.5.3
GHSA-8x88-c5mf-7j5wnode-tar: Negative tar entry size causes infinite loop in archive replacehigh[email protected]indirectfixed in 7.5.18
GHSA-9ppj-qmqm-q256node-tar Symlink Path Traversal via Drive-Relative Linkpathhigh[email protected]indirectfixed in 7.5.11
GHSA-qffp-2rhf-9h96tar has Hardlink Path Traversal via Drive-Relative Linkpathhigh[email protected]indirectfixed in 7.5.10
GHSA-r292-9mhp-454mnode-tar: Uncontrolled recursion in mapHas/filesFilter allows uncatchable stack-overflow DoS via crafted long-path tar with member selectionhigh[email protected]indirectfixed in 7.5.21
GHSA-r6q2-hw4h-h46wRace Condition in node-tar Path Reservations via Unicode Ligature Collisions on macOS APFShigh[email protected]indirectfixed in 7.5.4

4 more advisories in the dependencies endpoint.

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

packageregistryversionruntimesecrets
keymemnpm0.17.0–

Tools (0)

No tools observed. Local packages are never executed by the registry.

Schemas: list_tools.

Similar MCP servers

  • AiAkiv MemoryR2quality 100
    com.aiakiv/memory

    Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.

  • GraphmemL0
    io.github.sonic182/graphmem

    Shared local memory for coding agents: SQLite, semantic recall, linked entities, code navigation.

  • Total Agent MemoryL0
    io.github.vbcherepanov/total-agent-memory

    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

  • ReverieL0
    ai.knowall/reverie

    Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search

  • JunêL0
    io.github.Junemind/june-mcp

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

  • MaxGraphL0
    io.github.RuMemory/maxgraph

    Self-hosted persistent memory for AI agents: knowledge graph and hybrid search.

More from io.github.donggyun112

  • codecanvasL0
    io.github.donggyun112/codecanvas

    Python code intelligence for coding agents: call paths, control flow, and change impact.

Official server.json
{
  "name": "io.github.donggyun112/keymem",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.17.0",
  "packages": [
    {
      "version": "0.17.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "keymem",
      "registryType": "npm"
    }
  ],
  "repository": {
    "url": "https://github.com/donggyun112/keymem",
    "source": "github"
  },
  "description": "Associative key-graph memory for LLM agents — recall by association, not vector similarity."
}