KernelMind MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KERNELMIND_HOST | No | HTTP server bind address | 0.0.0.0 |
| KERNELMIND_PORT | No | HTTP server port | 8080 |
| KERNELMIND_NEO4J_URI | No | Neo4j URI (defaults from docker compose) | |
| KERNELMIND_REDIS_URL | No | Redis URL (defaults from docker compose) | |
| KERNELMIND_TRANSPORT | No | Transport protocol: stdio or streamable-http | stdio |
| KERNELMIND_QDRANT_URL | No | Qdrant URL (defaults from docker compose) | |
| KERNELMIND_S3_ENDPOINT | No | S3 endpoint (defaults from docker compose) | |
| KERNELMIND_POSTGRES_DSN | No | PostgreSQL connection string (defaults from docker compose) | |
| KERNELMIND_EMBEDDING_MODEL | Yes | Embedding model name (required) | |
| KERNELMIND_EMBEDDING_API_KEY | Yes | Embedding provider API key (required) | |
| KERNELMIND_EMBEDDING_BASE_URL | Yes | Embedding provider base URL (required) |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_kernel_codeA | Search for kernel code using hybrid search across all indexed data. Args: query: The search query string. repo: Optional repository to filter by. subsystem: Optional subsystem to filter by. limit: Maximum number of results to return. Returns: Dictionary containing results and correlated evidence sources. |
| lookup_symbolA | Look up a specific symbol (function, struct, macro) in kernel source. Args: name: The name of the symbol to look up. kind: Optional kind of symbol (e.g., 'function', 'struct'). repo: Optional repository to filter by. Returns: Dictionary containing location, definition, and evidence sources. |
| search_commitsA | Search kernel git commits by message, author, or subsystem. Args: query: Keywords to search in commit messages. author: Optional author filter. file_path: Optional file path filter. subsystem: Optional subsystem filter. limit: Max number of commits to return. Returns: Dictionary with matching commits and evidence sources. |
| get_commit_detailsA | Retrieve detailed metadata for a specific kernel commit SHA. Args: sha: Complete or prefix commit SHA. repo: Optional repository name filter. Returns: Dictionary with commit metadata and evidence sources. |
| get_file_historyA | Get commit history and symbol evolution for a kernel file path. Args: file_path: Relative file path in kernel tree. repo: Optional repository filter. limit: Max commits to return. Returns: Dictionary with file commit history and evidence sources. |
| blame_line_rangeA | Get commit attribution for a specific line range in a file. Args: file_path: Relative file path in kernel tree. start_line: Starting line number (1-indexed). end_line: Ending line number. repo: Optional repository filter. Returns: Dictionary with line range attributions and evidence sources. |
| search_patchesA | Search submitted kernel patches by query, submitter, or state. Args: query: Search terms for patch name. submitter: Optional submitter filter. state: Optional patch state filter. subsystem: Optional subsystem filter. limit: Max results. Returns: Dictionary of matching patches and evidence sources. |
| get_patch_detailsA | Retrieve full metadata and state transition history for a patch. Args: patch_id: Patchwork message/patch ID. Returns: Dictionary with patch details, history, and evidence sources. |
| search_lkmlA | Search Linux Kernel Mailing List threads by subject or excerpt. Args: query: Search keywords. subsystem: Optional subsystem filter. author: Optional from_addr filter. limit: Max results. Returns: Dictionary with matching threads and evidence sources. |
| get_thread_detailsB | Retrieve full details and body excerpt for an LKML thread. Args: message_id: Email message ID of the thread. Returns: Dictionary with thread metadata and evidence sources. |
| analyze_patch_seriesA | Analyze a series of kernel patches for risks, subsystems, and evidence. Args: patches: Sequence of patch dictionaries containing name/diff_content. subsystem_hint: Optional initial subsystem assumption. Returns: Dictionary with analysis summary, risk flags, and evidence sources. |
| search_docsA | Search kernel documentation files by query or subsystem. Args: query: Keywords to search in document titles and headings. subsystem: Optional subsystem filter (e.g. 'net', 'mm'). limit: Maximum number of documentation results to return. Returns: Dictionary containing matching 'docs' list and 'evidence_sources'. |
| get_doc_detailsA | Retrieve full content and section headings for a kernel document. Args: doc_id: Document file path (e.g. Documentation/net/core.rst). Returns: Dictionary containing document title, sections, and evidence_sources. |
| search_lwnA | Search Linux Weekly News (LWN) articles on kernel development. Args: query: Keywords to search in article titles and body. subsystem: Optional subsystem filter (e.g. 'mm', 'sched'). limit: Maximum number of articles to return. Returns: Dictionary containing 'articles' list and 'evidence_sources'. |
| get_lwn_articleA | Retrieve full details and symbol references for an LWN article. Args: article_id: Unique LWN article ID (e.g. LWN-900100). Returns: Dictionary containing article title, author, body, and evidence_sources. |
| analyze_subsystem_riskA | Analyze overall engineering risk and stability for a kernel subsystem. Args: subsystem: Kernel subsystem identifier (e.g. 'mm', 'sched', 'net'). time_range: Time period for analysis (default: '30d'). Returns: Dictionary containing risk_score, stability_rating, risk_factors, hardware_validation_required, summary, and evidence_sources. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| knowledge_gathering_prompt | Create a prompt for gathering knowledge about a kernel topic. Args: topic: The topic to research. Returns: Formatted prompt string. |
| code_search_prompt | Create a prompt for searching code related to a feature. Args: subsystem: The kernel subsystem. feature: The specific feature to search for. Returns: Formatted prompt string. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| list_indexed_repos | Return a list of indexed repositories. |
| list_subsystems | Return a list of tracked kernel subsystems. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Reinazhard/kernelmind-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server