Skip to main content
Glama
zhiyue

mgx-thinking-log-mcp

by zhiyue
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

mgx-thinking-log-mcp

An MCP (Model Context Protocol) server for downloading and reading MGX thinking logs. Enables AI agents to fetch and analyze MGX conversation logs programmatically.

Installation

npm install -g mgx-thinking-log-mcp

Related MCP server: roo-activity-logger

Quick Start

Claude Desktop / Cursor (Team Mode)

Add to your MCP config (claude_desktop_config.json or .cursor/mcp.json):

{
  "mcpServers": {
    "mgx-thinking-log": {
      "command": "npx",
      "args": ["-y", "mgx-thinking-log-mcp"],
      "env": {
        "MGX_TOKEN": "your-token-here"
      }
    }
  }
}

Claude Code

claude mcp add mgx-thinking-log -- npx -y mgx-thinking-log-mcp

Then set environment variable MGX_TOKEN or pass token per-request.

Environment Variables

Variable

Description

Default

MGX_TOKEN

Auth token (appended as ?token= to skip Bearer auth)

-

MGX_BASE_URL

Base URL for the MGX API

http://test-tool.deepwisdomai.com

Tools

get_thinking_logs

Fetch thinking logs for a chat. Returns log content as text for agent analysis.

Parameters:

  • chat_id (required) - The chat/conversation ID

  • env (optional) - Environment: prod, alpha, pre, us-test, us-test-2 (default: prod)

  • token (optional) - Auth token, overrides MGX_TOKEN env var

Example prompt:

Read the thinking logs for chat abc123 in prod environment

download_thinking_logs

Download thinking logs to a local file.

Parameters:

  • chat_id (required) - The chat/conversation ID

  • env (optional) - Environment (default: prod)

  • output_path (required) - Local file path to save logs

  • token (optional) - Auth token

Example prompt:

Download the logs for chat abc123 to /tmp/logs.txt

get_mgx_env

Fetch the mgxenv.json configuration for a specific chat version.

Parameters:

  • chat_id (required) - The chat/conversation ID

  • env (optional) - Environment (default: prod)

  • version (required) - Version number

  • token (optional) - Auth token

Example prompt:

Get the mgxenv config for chat abc123 version v2

Rate Limiting

The upstream API has a global rate limit. Keep concurrent requests under 10 without prior arrangement. For higher concurrency, contact the platform team.

Development

git clone <repo-url>
cd mgx-thinking-log-mcp
npm install
npm run build
npm start

License

MIT

Available Tools

3 tools
download_thinking_logsA

Download MGX thinking logs to a local file. Useful for saving large log files for later analysis.

ParametersJSON Schema
NameRequiredDescriptionDefault
envNoEnvironment: prod, alpha, pre, us-test, us-test-2prod
tokenNoAuth token (overrides MGX_TOKEN env var)
chat_idYesThe chat/conversation ID
output_pathYesLocal file path to save the downloaded logs

TDQS

A3.9/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry the behavioral burden. It clearly discloses that the tool downloads data to a local file, but it does not mention overwrite behavior, authentication requirements, environment handling, or any side effects beyond the file write. This is adequate but leaves gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The primary action is front-loaded, and the second sentence adds real usage context. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is enough for a straightforward download tool given full schema coverage, but it does not explicitly differentiate from get_thinking_logs or explain expected output/result behavior. Since there is no output schema, a bit more context about what happens after download would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are fully documented in the schema. The description itself adds no parameter-level detail but does contextually identify what is being downloaded. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Download MGX thinking logs to a local file.' It clearly distinguishes this tool from get_thinking_logs by emphasizing the local-file destination, which makes the purpose immediately recognizable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: 'Useful for saving large log files for later analysis.' It does not explicitly name get_thinking_logs as the alternative for viewing logs, but the rationale is clear enough to guide selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_mgx_envA

Fetch the mgxenv.json configuration for a specific MGX chat version. Returns environment config as JSON.

ParametersJSON Schema
NameRequiredDescriptionDefault
envNoEnvironment: prod, alpha, pre, us-test, us-test-2prod
tokenNoAuth token (overrides MGX_TOKEN env var)
chat_idYesThe chat/conversation ID
versionYesVersion number for the mgxenv file

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral burden. It does disclose that the operation is a fetch and that the return format is JSON, which implies a read-only action. However, it does not mention authentication requirements, error behavior, or potential side effects, leaving meaningful gaps for a tool with no annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no filler. The operation and return type are front-loaded, making it immediately scannable for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a relatively simple read tool, the description covers the core action and return shape. However, with no output schema and no annotations, it omits useful operational context such as authentication expectations, error cases, and more detailed return structure, so completeness is only adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and every parameter already has a meaningful description in the schema. The tool description adds no parameter-level detail beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('Fetch'), a specific resource ('mgxenv.json configuration'), and the targeting condition ('specific MGX chat version'). It also clearly distinguishes the tool from sibling tools like get_thinking_logs and download_thinking_logs by naming a different resource type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for retrieving environment configuration, but it does not explicitly state when to use it over sibling tools, nor does it mention exclusions or alternative functions. An agent must infer context from the tool name and resource.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_thinking_logsA

Fetch MGX thinking logs for a given chat. Returns the log content as text, suitable for agent analysis.

ParametersJSON Schema
NameRequiredDescriptionDefault
envNoEnvironment: prod, alpha, pre, us-test, us-test-2prod
tokenNoAuth token (overrides MGX_TOKEN env var). Appended as ?token= to skip Bearer auth
chat_idYesThe chat/conversation ID

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It discloses that the tool is a read operation ('Fetch') and that the result is text, which is useful. However, it does not mention auth requirements, potential large responses, or any side-effect-free assurance beyond the verb itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no filler. The core action and return type are front-loaded, making the description easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple fetch-style tool with one required parameter and no output schema, the description adequately explains what is returned (text). It could be slightly more complete by clarifying how this differs from download_thinking_logs, but that gap is already covered under usage guidelines.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents env, token, and chat_id. The description adds no parameter-level detail beyond 'for a given chat', which is acceptable given the schema's completeness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Fetch'), resource ('MGX thinking logs'), scope ('for a given chat'), and return type ('text'). It doesn't explicitly contrast with download_thinking_logs, though 'as text, suitable for agent analysis' hints at the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'suitable for agent analysis' implies this tool is for reading logs inline, but there is no explicit guidance about when to choose this over download_thinking_logs or when not to use it. Usage context is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.1
    • First observeddownload_thinking_logs
    • First observedget_mgx_env
    • First observedget_thinking_logs
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

A4/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct operation: fetching log content as text, downloading logs to a file, and retrieving environment config. The difference between get and download is clear—one returns content for analysis, the other persists to disk.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (get_, download_). The nouns are descriptive and aligned with the tool's function, with no mixed naming conventions.

Tool Count5/5

Three tools is a well-scoped count for a focused logging/configuration server. Each tool serves a distinct purpose and none are redundant or bloat.

Completeness4/5

Core retrieval operations are covered: getting logs, downloading logs, and fetching environment config. A minor gap is the lack of listing or searching available logs, but the tool set likely expects chat IDs as inputs, making the surface adequate.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • iai-personal-memory-engine

    CodeAbra
    A
    license
    A
    quality
    A
    maintenance
    A local MCP server that gives AI assistants a long-term memory by capturing sessions verbatim and surfacing relevant context automatically.
    15
    884
    MIT

  • roo-activity-logger

    annenpolka
    A
    license
    A
    quality
    C
    maintenance
    MCP server that automatically logs AI coding assistant activities such as command executions and code generation, saving them as JSON files for later search and analysis.
    3
    25
    MIT

  • log-mcp

    ascii766164696D
    A
    license
    A
    quality
    D
    maintenance
    MCP server for log file analysis. Gives LLMs the ability to efficiently analyze large log files without loading them into context.
    7
    100
    MIT

  • logbook-mcp

    aether-technologies
    A
    license
    Not graded
    quality
    D
    maintenance
    A local MCP server for AI agents to log activities, query logs, and leave notes for each other, featuring a web UI and REST API.
    MIT