### Install and Import ExampleLib Parser

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/rst/index.rst

Install ExampleLib using pip and import the parse function. This is the basic setup for parsing log files.

```python
pip install examplelib
```

```python
from examplelib import parse
result = parse(open("server.log"))
```

--------------------------------

### Clone and Setup jDocMunch-MCP

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/CONTRIBUTING.md

Use these commands to clone the repository, install the package in editable mode with test dependencies, and run the test suite.

```bash
git clone https://github.com/jgravelle/jdocmunch-mcp
cd jdocmunch-mcp
pip install -e ".[test]"
pytest tests/ -q
```

--------------------------------

### Initialize jDocMunch MCP with Hooks

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

One-command setup for jDocMunch MCP, including client detection, configuration patching, policy installation, enforcement hooks, and directory indexing. Use --dry-run to preview or --yes for non-interactive mode.

```bash
jdocmunch-mcp init
```

--------------------------------

### Verify mypackage Installation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/tests/fixtures/docs/sample.adoc

Run this command to confirm that mypackage has been installed correctly. This command checks the installed version.

```bash
mypackage --version
```

--------------------------------

### Install Package from Source

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/markdown/install.md

Clone the repository and install the package in editable mode, including development dependencies.

```bash
git clone https://github.com/example/repo.git
cd repo
pip install -e .[dev]
```

--------------------------------

### Install Package with Pip

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/markdown/install.md

Use this command for a quick installation of the package from PyPI.

```bash
pip install example-package
```

--------------------------------

### Install mypackage

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/tests/fixtures/docs/sample.adoc

Use this command to install the package via pip. Ensure Python 3.10 or later is installed.

```bash
pip install mypackage
```

--------------------------------

### Verify Package Installation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/markdown/install.md

Run this command to confirm that the package has been installed correctly and check its version.

```bash
example-cli --version
```

--------------------------------

### Initialize jDocMunch MCP Hooks Only

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Command to install only the jDocMunch MCP enforcement hooks without performing other setup steps.

```bash
jdocmunch-mcp init --hooks
```

--------------------------------

### Install jdocmunch-mcp

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/USER_GUIDE.md

Installation methods for the jdocmunch-mcp package.

```bash
pip install jdocmunch-mcp
```

```bash
uvx jdocmunch-mcp --help
```

```bash
git clone https://github.com/jgravelle/jdocmunch-mcp.git
cd jdocmunch-mcp
pip install -e .
```

--------------------------------

### Configure Claude Desktop MCP

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/USER_GUIDE.md

Configuration examples for integrating jdocmunch-mcp with Claude Desktop.

```json
{
  "mcpServers": {
    "jdocmunch": {
      "command": "uvx",
      "args": ["jdocmunch-mcp"]
    }
  }
}
```

```json
{
  "mcpServers": {
    "jdocmunch": {
      "command": "uvx",
      "args": ["jdocmunch-mcp"],
      "env": {
        "GITHUB_TOKEN": "ghp_...",
        "ANTHROPIC_API_KEY": "sk-ant-..."
      }
    }
  }
}
```

```json
{
  "mcpServers": {
    "jdocmunch": {
      "command": "uvx",
      "args": ["--with", "openai", "jdocmunch-mcp"],
      "env": {
        "MINIMAX_API_KEY": "mx-...",
        "JDOCMUNCH_SUMMARIZER_PROVIDER": "minimax"
      }
    }
  }
}
```

--------------------------------

### Example TOML Configuration

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/markdown/configuration.md

This TOML snippet shows the structure for configuring the application, including required and optional fields.

```toml
[default]
api_key = "..."
endpoint = "https://api.example.com"
timeout_seconds = 60
retry_count = 5
log_level = "DEBUG"
```

--------------------------------

### Import Libraries and Configure Environment

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/tests/fixtures/docs/sample.ipynb

Imports necessary libraries like pandas and numpy. Ensure these libraries are installed before running.

```python
import pandas as pd
import numpy as np

print('Libraries loaded')
```

--------------------------------

### Tool Response Metadata Example

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

This example shows the '_meta' envelope included in jDocMunch tool responses, detailing latency, token savings, and estimated costs avoided for the call.

```json
"_meta": {
  "latency_ms": 12,
  "sections_returned": 5,
  "tokens_saved": 1840,
  "total_tokens_saved": 94320,
  "cost_avoided": { "claude_opus": 0.0276, "gpt5_latest": 0.0184 },
  "total_cost_avoided": { "claude_opus": 1.4148, "gpt5_latest": 0.9432 }
}
```

--------------------------------

### Import and Parse Log File

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/notebook/quickstart.ipynb

Installs the library via pip and imports the parser. Use this for basic parsing of files that fit into memory.

```python
from examplelib import parse
result = parse(open('server.log'))
print(len(result), 'events')
```

--------------------------------

### Verify jDocMunch MCP Installation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Command to verify that jDocMunch MCP has been installed correctly by checking its help message.

```bash
jdocmunch-mcp --help
```

--------------------------------

### Install jDocMunch MCP

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Command to install the jDocMunch MCP package using pip. This is a prerequisite for using the tool.

```bash
pip install jdocmunch-mcp
```

--------------------------------

### Upgrade Pip and Wheel

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/markdown/install.md

If pip installation fails with a build error related to 'wheel', upgrade pip and wheel first.

```bash
pip install --upgrade pip wheel
```

--------------------------------

### Local Repository Indexing and Retrieval

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/USER_GUIDE.md

Example usage for indexing a local folder and retrieving its table of contents using the bare folder name.

```json
index_local: { "path": "/home/user/docs" }
get_toc:     { "repo": "docs" }
```

--------------------------------

### Get Pods with Wide Output

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/jDocMunch_Benchmark_Kubernetes.md

This command retrieves a list of running Pods and displays detailed information, including their IP addresses and the nodes they are scheduled on. This is useful for verifying Pod placement after applying configurations.

```bash
kubectl get pods --output=wide
```

--------------------------------

### Import and run mypackage

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/tests/fixtures/docs/sample.html

Basic implementation for initializing and executing the library.

```python
import mypackage
mypackage.run()
```

--------------------------------

### Configure ExampleLib Parser with ParserConfig

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/replay/corpus/rst/index.rst

Configure the parser by passing a ParserConfig instance. Use strict=True to raise ParseError for malformed lines.

```python
from examplelib import parse, ParserConfig
cfg = ParserConfig(strict=True, encoding="utf-8")
result = parse(open("server.log"), cfg)
```

--------------------------------

### Section ID Format Examples

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/USER_GUIDE.md

Examples of the hierarchical section ID format used for identifying documentation segments.

```text
owner/repo::README.md::installation#1
owner/repo::docs/config.md::installation/prerequisites#3
owner/repo::docs/config.md::usage/configuration/advanced-configuration#4
local/myproject::guide.md::quick-start#1
```

--------------------------------

### Index and Browse Documentation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/USER_GUIDE.md

Commands for indexing local folders and repositories.

```text
index_local:         { "path": "/path/to/docs" }
get_toc:             { "repo": "docs" }
get_document_outline: { "repo": "docs", "doc_path": "README.md" }
```

```text
index_repo:   { "url": "owner/repo" }
get_toc_tree: { "repo": "owner/repo" }
```

--------------------------------

### Example Stable Section IDs

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Provides concrete examples of stable section IDs generated by jDocMunch for different document structures and locations.

```text
owner/repo::docs/install.md::installation#1
```

```text
owner/repo::docs/install.md::installation/prerequisites#3
```

```text
owner/repo::README.md::usage/configuration/advanced-configuration#4
```

```text
local/myproject::guide.md::configuration#2
```

--------------------------------

### Index Local Documentation Folder

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Use this command to index a local directory containing documentation files.

```json
index_local:          { "path": "/path/to/docs" }
```

--------------------------------

### Initialize jCodeMunch and jDocMunch

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Commands to run initialization for both jCodeMunch and jDocMunch, ensuring all necessary components and hooks are set up for both tools.

```bash
jcodemunch-mcp init
jdocmunch-mcp init
```

--------------------------------

### Index GitHub Repository Documentation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Use this command to index documentation from a GitHub repository.

```json
index_repo:           { "url": "owner/repo" }
```

--------------------------------

### Get Document Outline

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Retrieves the section hierarchy for a specific document within a GitHub repository.

```json
get_document_outline: { "repo": "owner/repo", "doc_path": "docs/config.md" }
```

--------------------------------

### Get Specific Section Content

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Retrieves the full content of a specific section using its unique ID.

```json
get_section:          { "repo": "owner/repo", "section_id": "owner/repo::docs/config.md::authentication#1" }
```

--------------------------------

### Configure Local Documentation Indexing

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/SPEC.md

Use this JSON configuration to index a local documentation folder. Set `incremental` to `false` to force a full re-index.

```json
{
  "path": "/path/to/docs",
  "use_ai_summaries": true,
  "extra_ignore_patterns": ["drafts/**"],
  "follow_symlinks": false,
  "incremental": true
}
```

--------------------------------

### client-go Credential Plugins Documentation

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/benchmarks/jDocMunch_Benchmark_Kubernetes.md

Explains the purpose and usage of client-go credential plugins for external authentication protocols in Kubernetes tools.

```markdown
## client-go credential plugins
[stable since v1.22]

`k8s.io/client-go` and tools using it such as `kubectl` and `kubelet` are able to
execute an external command to receive user credentials.

This feature is intended for client side integrations with authentication protocols
not natively supported by `k8s.io/client-go` (LDAP, Kerberos, OAuth2, SAML, etc.).
The plugin implements the protocol specific logic, then returns opaque credentials
to use. Almost all credential plugin use cases require a server side component with
support for the webhook token authenticator to interpret the credential format
produced by the client plugin.

Note: Earlier versions of `kubectl` included built-in support for authenticating
to AKS and GKE, but this is no longer present.
```

--------------------------------

### Get Table of Contents (Flat List)

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Retrieves a flat list of sections in document order from a GitHub repository.

```json
get_toc:              { "repo": "owner/repo" }
```

--------------------------------

### Get Table of Contents (Tree Structure)

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Retrieves a nested tree structure of sections per document from a GitHub repository.

```json
get_toc_tree:         { "repo": "owner/repo" }
```

--------------------------------

### Configure OpenClaw MCP Server with AI Summaries

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

This configuration includes optional AI summary settings and an Anthropic API key.

```json
{
  "mcpServers": {
    "jdocmunch": {
      "command": "uvx",
      "args": ["jdocmunch-mcp"],
      "transport": "stdio",
      "env": {
        "ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
      }
    }
  }
}
```

--------------------------------

### Run Replay Benchmark

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/todo.md

Execute the replay benchmark against a specified baseline. The gate parameter controls the acceptable deviation.

```bash
run_replay --baseline <prev> --gate 0.02
```

--------------------------------

### Get Section Hierarchy for a Document

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/SPEC.md

Obtain the heading hierarchy for a single document within an indexed repository. This is lighter than `get_toc` if the document is already known.

```json
{
  "repo": "owner/repo",
  "doc_path": "docs/configuration.md"
}
```

--------------------------------

### Configure OpenClaw MCP Server Directly

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Add this JSON entry to `~/.openclaw/openclaw.json` to configure jDocMunch-MCP.

```json
{
  "mcpServers": {
    "jdocmunch": {
      "command": "uvx",
      "args": ["jdocmunch-mcp"],
      "transport": "stdio"
    }
  }
}
```

--------------------------------

### Section ID Format Example

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/SPEC.md

Illustrates the structure of section IDs used for referencing content. These IDs are hierarchical and include repository, document path, slug, and heading level.

```text
{repo}::{doc_path}::{slug}#{level}
```

```text
owner/repo::README.md::installation#1
```

```text
owner/repo::docs/config.md::authentication-options#2
```

```text
local/myproject::guide.md::quick-start#1
```

--------------------------------

### Configure Agent System Prompt File in OpenClaw

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/README.md

Point your OpenClaw agent to its system prompt file in `~/.openclaw/openclaw.json`.

```json
{
  "agents": {
    "named": {
      "researcher": {
        "systemPromptFile": "~/.openclaw/agents/researcher.md"
      }
    }
  }
}
```

--------------------------------

### Configure jdocmunch tool profile via environment variables

Source: https://github.com/jgravelle/jdocmunch-mcp/blob/master/CHANGELOG.md

Set the JDOCMUNCH_TOOL_PROFILE environment variable to 'core' to limit the number of tools to 13, fitting under the 50-tool cap imposed by Google Antigravity.

```json
// per-server env vars
"jdocmunch": { "env": { "JDOCMUNCH_TOOL_PROFILE": "core" } }
```