protogrid
Sign inAdd to your agent

Search / io.github.yarnabrina/mcp-learning

Learning Model Context Protocol

L0· runs locally

Basic arithmetic tools with natural-language expression parsing and evaluation.

v0.3.0 · 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–not scored
Trust96of 100
Packages1
Tools seen0

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "--from",
        "mcp-learning",
        "mcp-server",
        "mcp-learning==0.3.0",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--streamable_http_path",
        "/mcp"
      ],
      "env": {
        "DEBUG": "false",
        "RUNTIME_ENVIRONMENT": "local",
        "LOG_LEVEL": "INFO",
        "JSON_RESPONSE": "false",
        "STATELESS_HTTP": "false"
      }
    }
  }
}
claude mcp add mcp-learning -e "DEBUG=false" -e "RUNTIME_ENVIRONMENT=local" -e "LOG_LEVEL=INFO" -e "JSON_RESPONSE=false" -e "STATELESS_HTTP=false" -- uvx --from mcp-learning mcp-server mcp-learning==0.3.0 --host 127.0.0.1 --port 8000 --streamable_http_path /mcp
[mcp_servers.mcp-learning]
command = "uvx"
args = ["--from", "mcp-learning", "mcp-server", "mcp-learning==0.3.0", "--host", "127.0.0.1", "--port", "8000", "--streamable_http_path", "/mcp"]
env = { "DEBUG" = "false", "RUNTIME_ENVIRONMENT" = "local", "LOG_LEVEL" = "INFO", "JSON_RESPONSE" = "false", "STATELESS_HTTP" = "false" }

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcp-learning": {
      "type": "local",
      "command": [
        "uvx",
        "--from",
        "mcp-learning",
        "mcp-server",
        "mcp-learning==0.3.0",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--streamable_http_path",
        "/mcp"
      ],
      "enabled": true,
      "environment": {
        "DEBUG": "false",
        "RUNTIME_ENVIRONMENT": "local",
        "LOG_LEVEL": "INFO",
        "JSON_RESPONSE": "false",
        "STATELESS_HTTP": "false"
      }
    }
  }
}
{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "--from",
        "mcp-learning",
        "mcp-server",
        "mcp-learning==0.3.0",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--streamable_http_path",
        "/mcp"
      ],
      "env": {
        "DEBUG": "false",
        "RUNTIME_ENVIRONMENT": "local",
        "LOG_LEVEL": "INFO",
        "JSON_RESPONSE": "false",
        "STATELESS_HTTP": "false"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-learning&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb20iLCJtY3AtbGVhcm5pbmciLCJtY3Atc2VydmVyIiwibWNwLWxlYXJuaW5nPT0wLjMuMCIsIi0taG9zdCIsIjEyNy4wLjAuMSIsIi0tcG9ydCIsIjgwMDAiLCItLXN0cmVhbWFibGVfaHR0cF9wYXRoIiwiL21jcCJdLCJlbnYiOnsiREVCVUciOiJmYWxzZSIsIlJVTlRJTUVfRU5WSVJPTk1FTlQiOiJsb2NhbCIsIkxPR19MRVZFTCI6IklORk8iLCJKU09OX1JFU1BPTlNFIjoiZmFsc2UiLCJTVEFURUxFU1NfSFRUUCI6ImZhbHNlIn19"
}
{
  "servers": {
    "mcp-learning": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "mcp-learning",
        "mcp-server",
        "mcp-learning==0.3.0",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--streamable_http_path",
        "/mcp"
      ],
      "env": {
        "DEBUG": "false",
        "RUNTIME_ENVIRONMENT": "local",
        "LOG_LEVEL": "INFO",
        "JSON_RESPONSE": "false",
        "STATELESS_HTTP": "false"
      }
    }
  }
}
{
  "mcpServers": {
    "mcp-learning": {
      "command": "uvx",
      "args": [
        "--from",
        "mcp-learning",
        "mcp-server",
        "mcp-learning==0.3.0",
        "--host",
        "127.0.0.1",
        "--port",
        "8000",
        "--streamable_http_path",
        "/mcp"
      ],
      "env": {
        "DEBUG": "false",
        "RUNTIME_ENVIRONMENT": "local",
        "LOG_LEVEL": "INFO",
        "JSON_RESPONSE": "false",
        "STATELESS_HTTP": "false"
      }
    }
  }
}
extensions:
  "mcp-learning":
    enabled: true
    name: "mcp-learning"
    type: stdio
    cmd: "uvx"
    args:
      - "--from"
      - "mcp-learning"
      - "mcp-server"
      - "mcp-learning==0.3.0"
      - "--host"
      - "127.0.0.1"
      - "--port"
      - "8000"
      - "--streamable_http_path"
      - "/mcp"
    envs:
      "DEBUG": "false"
      "RUNTIME_ENVIRONMENT": "local"
      "LOG_LEVEL": "INFO"
      "JSON_RESPONSE": "false"
      "STATELESS_HTTP": "false"
    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
dependencies100 · weight 15
  • pass
    deps.known_vulnsno known advisory in 73 resolved packages
  • pass
    deps.mcp_sdk_versionmcp 2.3.0, no known advisory
  • pass
    deps.resolvable[email protected] resolved: 73 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 96 / 100

provenance90
livenessn/a
freshness100
hygiene100

+repository +namespace-matches-repo +website ~liveness-unmeasured +updated-2d-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] PyPI72 dependencies, resolved · MCP SDK mcp 2.3.0 · advisories checked 2026-10-19

No known advisory affects this dependency graph.

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
mcp-learningpypi0.3.0uvx

Tools (0)

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

Schemas: list_tools.

Similar MCP servers

  • mcp-serverL0
    io.github.cap-js/mcp-server

    Model Context Protocol (MCP) server for AI-assisted development of CAP applications.

  • Knowledge ForestL0
    io.github.znecho9/knowledge-forest-mcp

    Local-first personal knowledge and learning memory for AI tutors with evidence-gated mastery.

  • contextq-mcpR2quality 100
    io.github.contextq/contextq-mcp

    Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.

  • ContextStreamR2quality 100
    io.contextstream/mcp

    Persistent memory and cross-session learning for AI coding assistants (hosted remote MCP).

  • calc-mcpL0
    io.github.coo-quack/calc-mcp

    21 MCP tools for math, randomness, dates, encoding, hashing, and more — deterministic and accurate.

  • calculator-mcpL0
    io.github.tech-sushant/calculator-mcp

    A simple Model Context Protocol calculator server

Official server.json
{
  "name": "io.github.yarnabrina/mcp-learning",
  "title": "Learning Model Context Protocol",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "version": "0.3.0",
  "packages": [
    {
      "version": "0.3.0",
      "transport": {
        "url": "http://127.0.0.1:8000/mcp",
        "type": "streamable-http"
      },
      "identifier": "mcp-learning",
      "runtimeHint": "uvx",
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "packageArguments": [
        {
          "name": "--host",
          "type": "named",
          "format": "string",
          "default": "127.0.0.1",
          "description": "Local bind address for the Streamable HTTP server."
        },
        {
          "name": "--port",
          "type": "named",
          "format": "number",
          "default": "8000",
          "description": "Local port for the Streamable HTTP server."
        },
        {
          "name": "--streamable_http_path",
          "type": "named",
          "format": "string",
          "default": "/mcp",
          "description": "Endpoint path for the Streamable HTTP server."
        }
      ],
      "runtimeArguments": [
        {
          "name": "--from",
          "type": "named",
          "value": "mcp-learning",
          "format": "string",
          "isRequired": true,
          "description": "Resolve console scripts from the published PyPI package."
        },
        {
          "type": "positional",
          "value": "mcp-server",
          "format": "string",
          "valueHint": "command",
          "isRequired": true,
          "description": "Invoke the entry point console script that starts the MCP server."
        }
      ],
      "environmentVariables": [
        {
          "name": "DEBUG",
          "format": "boolean",
          "default": "false",
          "description": "Enable additional debug logging output."
        },
        {
          "name": "RUNTIME_ENVIRONMENT",
          "format": "string",
          "choices": [
            "local",
            "production"
          ],
          "default": "local",
          "description": "Logging/runtime environment."
        },
        {
          "name": "LOG_LEVEL",
          "format": "string",
          "choices": [
            "DEBUG",
            "INFO",
            "WARNING",
            "ERROR",
            "CRITICAL"
          ],
          "default": "INFO",
          "description": "Log level for server output; the server defaults to INFO."
        },
        {
          "name": "LOG_FILE",
          "format": "filepath",
          "description": "Optional path for a server log file."
        },
        {
          "name": "JSON_RESPONSE",
          "format": "boolean",
          "default": "false",
          "description": "Return JSON payloads for HTTP responses instead of newline-delimited JSON."
        },
        {
          "name": "STATELESS_HTTP",
          "format": "boolean",
          "default": "false",
          "description": "Disable HTTP keep-alive to serve each request independently."
        }
      ]
    }
  ],
  "repository": {
    "id": "1026553889",
    "url": "https://github.com/yarnabrina/learn-model-context-protocol",
    "source": "github"
  },
  "websiteUrl": "https://yarnabrina.github.io/learn-model-context-protocol/",
  "description": "Basic arithmetic tools with natural-language expression parsing and evaluation."
}