Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "engrava": {
      "command": "uvx",
      "args": [
        "engrava-mcp==0.7.0"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "${ENGRAVA_DB_PATH}"
      }
    }
  }
}

claude mcp add engrava -e "ENGRAVA_DB_PATH=${ENGRAVA_DB_PATH}" -- uvx engrava-mcp==0.7.0

[mcp_servers.engrava]
command = "uvx"
args = ["engrava-mcp==0.7.0"]
env = { "ENGRAVA_DB_PATH" = "${ENGRAVA_DB_PATH}" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "engrava": {
      "type": "local",
      "command": [
        "uvx",
        "engrava-mcp==0.7.0"
      ],
      "enabled": true,
      "environment": {
        "ENGRAVA_DB_PATH": "{env:ENGRAVA_DB_PATH}"
      }
    }
  }
}

{
  "mcpServers": {
    "engrava": {
      "command": "uvx",
      "args": [
        "engrava-mcp==0.7.0"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "${ENGRAVA_DB_PATH}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=engrava&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJlbmdyYXZhLW1jcD09MC43LjAiXSwiZW52Ijp7IkVOR1JBVkFfREJfUEFUSCI6IiR7RU5HUkFWQV9EQl9QQVRIfSJ9fQ%3D%3D"
}

{
  "servers": {
    "engrava": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "engrava-mcp==0.7.0"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "${ENGRAVA_DB_PATH}"
      }
    }
  }
}

{
  "mcpServers": {
    "engrava": {
      "command": "uvx",
      "args": [
        "engrava-mcp==0.7.0"
      ],
      "env": {
        "ENGRAVA_DB_PATH": "${ENGRAVA_DB_PATH}"
      }
    }
  }
}

extensions:
  "engrava":
    enabled: true
    name: "engrava"
    type: stdio
    cmd: "uvx"
    args:
      - "engrava-mcp==0.7.0"
    envs:
      "ENGRAVA_DB_PATH": "${ENGRAVA_DB_PATH}"
    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

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know [email protected]

Tool list unknown · checked 2026-10-19 10:52 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 96 / 100

provenance90

livenessn/a

freshness100

hygiene100

+repository +namespace-matches-repo +dns-namespace ~liveness-unmeasured +updated-17d-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] PyPIthis version is not known to the dependency resolver

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

package	registry	version	runtime	secrets
`engrava-mcp`	pypi	0.7.0	–

Tools (0)

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

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.sovantica/engrava",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.7.0",
  "packages": [
    {
      "version": "0.7.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "engrava-mcp",
      "registryType": "pypi",
      "environmentVariables": [
        {
          "name": "ENGRAVA_DB_PATH",
          "format": "filepath",
          "isRequired": true,
          "description": "Absolute path to the SQLite database file. Created if missing; its directory must exist. Enough on its own: full-text search, the graph and MindQL work, but vector search needs ENGRAVA_MCP_CONFIG."
        },
        {
          "name": "ENGRAVA_MCP_CONFIG",
          "format": "filepath",
          "description": "Absolute path to an engrava.yaml, for an embedding provider (vector search) and the thought/edge journal. When set, it takes precedence and ENGRAVA_DB_PATH is not read."
        },
        {
          "name": "ENGRAVA_MCP_READ_ONLY",
          "format": "boolean",
          "description": "Set to true to register no write tools."
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/sovantica/engrava-mcp",
    "source": "github"
  },
  "description": "MindQL queries, hybrid search, and a thought graph - read/write memory for AI agents."
}