protogrid

Search / io.github.pournasserian/mcp-my-site

mcp-my-site

R0· no sign-in

Search and fetch tools for one website, served from an index you build with the mcpmysite crawler.

v0.2.2 · active · repository · website · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality87new
Trust95of 100
Uptime, 30 days92%
Latency p50182 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "mcp-my-site": {
      "type": "http",
      "url": "https://ai.pournasserian.com/mcp"
    }
  }
}
claude mcp add --transport http mcp-my-site https://ai.pournasserian.com/mcp
[mcp_servers.mcp-my-site]
url = "https://ai.pournasserian.com/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcp-my-site": {
      "type": "remote",
      "url": "https://ai.pournasserian.com/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "mcp-my-site": {
      "type": "http",
      "url": "https://ai.pournasserian.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-my-site&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYWkucG91cm5hc3Nlcmlhbi5jb20vbWNwIn0%3D"
}
{
  "servers": {
    "mcp-my-site": {
      "type": "http",
      "url": "https://ai.pournasserian.com/mcp"
    }
  }
}
{
  "mcpServers": {
    "mcp-my-site": {
      "httpUrl": "https://ai.pournasserian.com/mcp"
    }
  }
}
extensions:
  "mcp-my-site":
    enabled: true
    name: "mcp-my-site"
    type: streamable_http
    uri: "https://ai.pournasserian.com/mcp"
    timeout: 300

Quality 87 / 100new

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use
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 hygiene86 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations2 of 2 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search (destructiveHint); fetch (destructiveHint)
  • pass
    tools.token_costabout 317 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stabilityn/a · weight 15
  • n/a
    stability.changes, stability.rug_pulltool history recorded for 2 of the 7 days needed
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

2 tools, about 317 tokens to load them all · tool set 479aa1313e5a · tools last changed 2026-10-19 · checked 2026-10-20 20:14 UTC

Tool changes

  • searchchangeddescription
    before

    Searches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 51 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

    after · 96% of words in common

    Searches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 52 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

  • searchchangeddescription
    before

    Searches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 48 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

    after · 96% of words in common

    Searches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 51 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

Full history: list_changes · trend: quality JSON.

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 95 / 100

provenance90
liveness97
freshness100
hygiene95

+repository +namespace-matches-repo +website +reachable +uptime-92% +updated-2d-ago -unpinned-packages(1)

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://ai.pournasserian.com/mcp streamable-httpnoneyes92%182 ms2026-07-282026-10-20
packageregistryversionruntimesecrets
ghcr.io/pournasserian/mcp-my-site:0.2.2ociunpinneddockerAI_API_KEY

Tools (2)

fetchread-onlyReturns the full content of one page of the website as Markdown in text, with its title, description, language and last modified date. Pass the id (or url) of a search result.
searchread-onlySearches the website Amir Pournasserian (https://pournasserian.com/): Serial entrepreneur and hands-on AI architect. I build AI and platform systems that have to keep working once they meet production, compliance and scale. Hybrid keyword and semantic search over its 52 pages; returns the best matching pages with a short snippet each. Call fetch with a result's id or URL to read the whole page.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.pournasserian/mcp-my-site",
  "title": "mcp-my-site",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://ai.pournasserian.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.2.2",
  "packages": [
    {
      "transport": {
        "url": "http://localhost:8080/mcp",
        "type": "streamable-http"
      },
      "identifier": "ghcr.io/pournasserian/mcp-my-site:0.2.2",
      "runtimeHint": "docker",
      "registryType": "oci",
      "runtimeArguments": [
        {
          "name": "-p",
          "type": "named",
          "value": "8080:8080",
          "description": "Publish the server's port 8080 on the host."
        },
        {
          "name": "-v",
          "type": "named",
          "value": "{index_dir}:/index:ro",
          "variables": {
            "index_dir": {
              "format": "filepath",
              "isRequired": true,
              "description": "Absolute path of the index folder on the host."
            }
          },
          "isRequired": true,
          "description": "Mount the index folder built by `mcpmysite build` into the container."
        }
      ],
      "environmentVariables": [
        {
          "name": "Index__Path",
          "default": "/index",
          "isRequired": true,
          "description": "Folder inside the container that holds the index, the target of the mount above."
        },
        {
          "name": "AI_API_KEY",
          "isSecret": true,
          "description": "API key for the embeddings provider, needed only to serve a hybrid index. Leave it unset for a keyword-only index."
        }
      ]
    }
  ],
  "repository": {
    "id": "1413689394",
    "url": "https://github.com/pournasserian/mcp-my-site",
    "source": "github"
  },
  "websiteUrl": "https://github.com/pournasserian/mcp-my-site#readme",
  "description": "Search and fetch tools for one website, served from an index you build with the mcpmysite crawler."
}