protogrid
Sign inAdd to your agent

Search / io.github.datolabs-io/mcp-toolsearch-proxy

Tool Search Proxy

L0· runs locally

Lets a model search and call a large MCP tool catalog through five tools instead of loading it

v0.9.0 · active · repository · website · 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–new
Trust94of 100
Packages2
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "mcp-toolsearch-proxy": {
      "command": "docker",
      "args": [
        "-p",
        "127.0.0.1:8000:8000",
        "-e",
        "TOOLSEARCH_UPSTREAM",
        "-e",
        "TOOLSEARCH_EMBEDDER",
        "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
      ],
      "env": {
        "TOOLSEARCH_UPSTREAM": "${TOOLSEARCH_UPSTREAM}",
        "TOOLSEARCH_EMBEDDER": "none"
      }
    }
  }
}
claude mcp add mcp-toolsearch-proxy -e "TOOLSEARCH_UPSTREAM=${TOOLSEARCH_UPSTREAM}" -e "TOOLSEARCH_EMBEDDER=none" -- docker -p 127.0.0.1:8000:8000 -e TOOLSEARCH_UPSTREAM -e TOOLSEARCH_EMBEDDER ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0
[mcp_servers.mcp-toolsearch-proxy]
command = "docker"
args = ["-p", "127.0.0.1:8000:8000", "-e", "TOOLSEARCH_UPSTREAM", "-e", "TOOLSEARCH_EMBEDDER", "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"]
env = { "TOOLSEARCH_UPSTREAM" = "${TOOLSEARCH_UPSTREAM}", "TOOLSEARCH_EMBEDDER" = "none" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcp-toolsearch-proxy": {
      "type": "local",
      "command": [
        "docker",
        "-p",
        "127.0.0.1:8000:8000",
        "-e",
        "TOOLSEARCH_UPSTREAM",
        "-e",
        "TOOLSEARCH_EMBEDDER",
        "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
      ],
      "enabled": true,
      "environment": {
        "TOOLSEARCH_UPSTREAM": "{env:TOOLSEARCH_UPSTREAM}",
        "TOOLSEARCH_EMBEDDER": "none"
      }
    }
  }
}
{
  "mcpServers": {
    "mcp-toolsearch-proxy": {
      "command": "docker",
      "args": [
        "-p",
        "127.0.0.1:8000:8000",
        "-e",
        "TOOLSEARCH_UPSTREAM",
        "-e",
        "TOOLSEARCH_EMBEDDER",
        "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
      ],
      "env": {
        "TOOLSEARCH_UPSTREAM": "${TOOLSEARCH_UPSTREAM}",
        "TOOLSEARCH_EMBEDDER": "none"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-toolsearch-proxy&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyItcCIsIjEyNy4wLjAuMTo4MDAwOjgwMDAiLCItZSIsIlRPT0xTRUFSQ0hfVVBTVFJFQU0iLCItZSIsIlRPT0xTRUFSQ0hfRU1CRURERVIiLCJnaGNyLmlvL2RhdG9sYWJzLWlvL21jcC10b29sc2VhcmNoLXByb3h5OjAuOS4wIl0sImVudiI6eyJUT09MU0VBUkNIX1VQU1RSRUFNIjoiJHtUT09MU0VBUkNIX1VQU1RSRUFNfSIsIlRPT0xTRUFSQ0hfRU1CRURERVIiOiJub25lIn19"
}
{
  "servers": {
    "mcp-toolsearch-proxy": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "-p",
        "127.0.0.1:8000:8000",
        "-e",
        "TOOLSEARCH_UPSTREAM",
        "-e",
        "TOOLSEARCH_EMBEDDER",
        "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
      ],
      "env": {
        "TOOLSEARCH_UPSTREAM": "${TOOLSEARCH_UPSTREAM}",
        "TOOLSEARCH_EMBEDDER": "none"
      }
    }
  }
}
{
  "mcpServers": {
    "mcp-toolsearch-proxy": {
      "command": "docker",
      "args": [
        "-p",
        "127.0.0.1:8000:8000",
        "-e",
        "TOOLSEARCH_UPSTREAM",
        "-e",
        "TOOLSEARCH_EMBEDDER",
        "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
      ],
      "env": {
        "TOOLSEARCH_UPSTREAM": "${TOOLSEARCH_UPSTREAM}",
        "TOOLSEARCH_EMBEDDER": "none"
      }
    }
  }
}
extensions:
  "mcp-toolsearch-proxy":
    enabled: true
    name: "mcp-toolsearch-proxy"
    type: stdio
    cmd: "docker"
    args:
      - "-p"
      - "127.0.0.1:8000:8000"
      - "-e"
      - "TOOLSEARCH_UPSTREAM"
      - "-e"
      - "TOOLSEARCH_EMBEDDER"
      - "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0"
    envs:
      "TOOLSEARCH_UPSTREAM": "${TOOLSEARCH_UPSTREAM}"
      "TOOLSEARCH_EMBEDDER": "none"
    timeout: 300

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

Quality – / 100new

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.resolvableno npm or PyPI package

Tool list unknown · checked 2026-11-07 17:28 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 94 / 100

provenance90
livenessn/a
freshness100
hygiene95

+repository +namespace-matches-repo +website ~liveness-unmeasured +updated-4d-ago -unpinned-packages(2)

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

Endpoints

packageregistryversionruntimesecrets
ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0ociunpinned–
ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0ociunpinned–

Tools (0)

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

Schemas: list_tools.

Similar MCP servers

  • Tool Filter MCPL0
    io.github.respawn-llc/tool-filter-mcp

    MCP proxy server that filters tools from upstream MCP servers via regex-based deny list

  • Google_search_consoleR0quality 77
    io.github.pipeworx-io/google_search_console

    Google Search Console MCP Pack

  • mcp-loomL0
    io.github.buttonmonkey/mcp-loom

    Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.

  • quanticdata-mcpR2quality 85
    io.github.quantumproxies/quanticdata-mcp

    Live web access for agents: scrape, SERP search, crawl/map, 100+ collectors, datasets, proxies.

  • SerperR0quality 77
    io.github.pipeworx-io/serper

    Serper MCP — wraps the Serper Google Search API (serper.dev)

  • context-firewallL0
    io.github.Alepha188838884/context-firewall

    Local MCP proxy: collapses N servers' tools into 4 meta-tools and compresses large tool outputs.

Official server.json
{
  "name": "io.github.datolabs-io/mcp-toolsearch-proxy",
  "title": "Tool Search Proxy",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.9.0",
  "packages": [
    {
      "transport": {
        "url": "http://localhost:8000/mcp",
        "type": "streamable-http"
      },
      "identifier": "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0",
      "registryType": "oci",
      "runtimeArguments": [
        {
          "name": "-p",
          "type": "named",
          "value": "127.0.0.1:8000:8000",
          "description": "Publish the proxy's port on localhost only: the proxy has no authentication of its own"
        }
      ],
      "environmentVariables": [
        {
          "name": "TOOLSEARCH_UPSTREAM",
          "isRequired": true,
          "description": "Streamable HTTP URL of the MCP server whose tools are searched, such as a gateway"
        },
        {
          "name": "TOOLSEARCH_EMBEDDER",
          "choices": [
            "builtin",
            "none"
          ],
          "default": "none",
          "description": "builtin for semantic search, which needs the model in a volume at /model (see docs/deploy.md); none for lexical search only"
        }
      ]
    },
    {
      "transport": {
        "type": "stdio"
      },
      "identifier": "ghcr.io/datolabs-io/mcp-toolsearch-proxy:0.9.0",
      "registryType": "oci",
      "environmentVariables": [
        {
          "name": "MCP_TRANSPORT",
          "value": "stdio",
          "isRequired": true,
          "description": "stdio: MCP on standard input and output. Upstream requests then carry no token, so this suits only an upstream that needs no authentication"
        },
        {
          "name": "TOOLSEARCH_UPSTREAM",
          "isRequired": true,
          "description": "Streamable HTTP URL of an MCP server that needs no authentication"
        },
        {
          "name": "TOOLSEARCH_EMBEDDER",
          "choices": [
            "builtin",
            "none"
          ],
          "default": "none",
          "description": "builtin for semantic search, which needs the model in a volume at /model (see docs/deploy.md); none for lexical search only"
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/datolabs-io/mcp-toolsearch-proxy",
    "source": "github"
  },
  "websiteUrl": "https://github.com/datolabs-io/mcp-toolsearch-proxy#readme",
  "description": "Lets a model search and call a large MCP tool catalog through five tools instead of loading it"
}