Skip to main content
Glama
kongyo2

MCP Dev MCP

by kongyo2
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription
mcpdev_inspector_list_toolsA

List all available tools from a target MCP server.

Use this to discover what tools a target MCP server provides. Returns tool names, descriptions, and input schemas.

Args:

  • target (string): Target MCP server - command (e.g., 'node server.js') or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type (auto-detected if not specified)

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

Returns: JSON object with 'tools' array containing tool definitions.

Examples:

  • Local server: { target: "node dist/index.js", transport: "stdio" }

  • Remote SSE: { target: "https://mcp.example.com/sse", transport: "sse" }

mcpdev_inspector_call_toolA

Execute a tool on a target MCP server.

Use this to invoke a specific tool on the target server with provided arguments.

Args:

  • target (string): Target MCP server - command or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

  • tool_name (string): Name of the tool to call

  • tool_args (object): Arguments to pass to the tool

Returns: The tool's response content.

Examples:

  • { target: "node server.js", tool_name: "get_weather", tool_args: { city: "Tokyo" } }

mcpdev_inspector_list_resourcesA

List all available resources from a target MCP server.

Use this to discover what resources (data/content) a target MCP server exposes.

Args:

  • target (string): Target MCP server - command or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

Returns: JSON object with 'resources' array containing resource URIs and metadata.

mcpdev_inspector_read_resourceA

Read a specific resource from a target MCP server.

Use this to fetch the content of a resource by its URI.

Args:

  • target (string): Target MCP server - command or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

  • uri (string): Resource URI to read

Returns: The resource content (text or base64-encoded blob).

mcpdev_inspector_list_promptsA

List all available prompts from a target MCP server.

Use this to discover what prompt templates a target MCP server provides.

Args:

  • target (string): Target MCP server - command or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

Returns: JSON object with 'prompts' array containing prompt definitions.

mcpdev_inspector_get_promptA

Get a specific prompt from a target MCP server.

Use this to retrieve and render a prompt template with provided arguments.

Args:

  • target (string): Target MCP server - command or URL

  • transport ('stdio' | 'sse' | 'http'): Transport type

  • timeout_ms (number): Timeout in milliseconds (default: 60000)

  • prompt_name (string): Name of the prompt to get

  • prompt_args (object): Arguments to pass to the prompt template

Returns: The rendered prompt messages.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: call_tool executes tools, get_prompt retrieves prompts, list_prompts lists prompts, list_resources lists resources, list_tools lists tools, and read_resource reads resources. The descriptions clearly differentiate their functions, making misselection unlikely.

Naming Consistency5/5

All tools follow a consistent snake_case pattern with the prefix 'mcpdev_inspector_' followed by a verb_noun structure (e.g., call_tool, get_prompt, list_prompts). This predictability makes the tool set easy to navigate and understand.

Tool Count5/5

With 6 tools, this server is well-scoped for its purpose of inspecting and interacting with MCP servers. Each tool serves a specific role in discovery and execution, with no redundancy, making the count appropriate and efficient.

Completeness5/5

The tool set provides complete coverage for the MCP server inspection domain, including listing tools, prompts, and resources, reading resources, getting prompts, and calling tools. There are no obvious gaps, enabling agents to perform all essential inspection and interaction tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources