okf-tools
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| 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 |
|---|---|
| commit_conceptC | Commit a new concept to the knowledge bundle. Creates a concept file with the given title, type, and content. Optionally checks for duplicate concepts before committing. |
| init_bundleA | Initialize a new OKF knowledge bundle at the specified path. Creates .okf/config.json, a root index.md, and updates .gitignore if in a git repo. This is the only tool that does not require a pre-configured bundle. |
| update_conceptA | Update an existing concept in the bundle. Applies only the provided fields to the concept, leaving unspecified fields unchanged. Re-embeds the content and updates the vector index. |
| move_conceptA | Move or rename a concept within the bundle. Changes the concept's location (and therefore its concept_id) without losing content, metadata, or vector-index history. Optionally updates the title in frontmatter at the same time. Examples:
|
| delete_conceptA | Delete a concept from the bundle by its concept_id. |
| show_conceptA | Show the full details of a concept by its concept_id. Returns all frontmatter fields and the complete markdown body. |
| reindexA | Rebuild the vector index for the knowledge bundle. Performs an incremental reindex by default (only processes changed files). Set full=True to discard the existing index and rebuild from scratch. Returns a JSON summary with counts of added, updated, removed, skipped concepts and the total number of indexed concepts. |
| fetch_conceptsA | Search the knowledge bundle using natural language queries. Returns a ranked list of matching concepts with scores and snippets. Supports hybrid (semantic + keyword), keyword-only, or semantic-only modes. |
| list_conceptsB | List concepts in the knowledge bundle with optional filters. Returns a filtered, sorted list of concepts. Supports filtering by type, tags, modification date, and path prefix. |
| get_statsA | Return bundle health statistics. Returns concept count, type/tag distributions, last reindex timestamp, and the number of concepts pending re-embedding. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- 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/hdean-ssp/okf-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server