Capacities MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAPACITIES_API_TOKEN | Yes | Personal API token for Capacities API 2.0 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| append_content_markdownA | Explicitly append Markdown to an existing object. Use append_content for the preferred structural JSON-block workflow. Markdown conversion is lossy for exact underline styling, toggle details, Grid layout, and HTML background colors; inspect lossReport. |
| append_contentA | Append structural API 2.0 blocks to an existing object, optionally at the start, after a known block, inside a parent block, or in a specific block property. |
| append_daily_note_markdownA | Explicitly append Markdown to a Capacities daily note. Use append_daily_note for the preferred structural JSON-block workflow. The API queues this write asynchronously and lossReport is preflight-only; Markdown conversion is lossy for exact underline styling, toggle details, Grid layout, and HTML background colors. |
| append_daily_noteA | Append structural API 2.0 blocks to today's or a specified Capacities daily note. The Capacities API queues this write asynchronously, so success means accepted/queued rather than immediately readable. |
| create_object_from_url_markdownA | Explicitly create a Capacities web-resource object from a URL and Markdown notes. Use create_object_from_url for the preferred structural-block workflow; conversion is lossy for exact underline styling, toggle details, Grid layout, and HTML background colors, so inspect lossReport. |
| create_object_from_urlA | Create a Capacities web-resource object from a URL, optionally adding structural API 2.0 blocks. This is the preferred URL-import tool; use create_object_from_url_markdown only when Markdown authoring is specifically requested. |
| create_object_markdownA | Explicitly create a Capacities object from a Markdown body. Use create_object for the preferred structural JSON-block workflow; Markdown conversion is lossy for exact underline styling, toggle details, Grid layout, and HTML background colors, so inspect lossReport. |
| create_objectA | Preferred structural creator for Page, Tag, Task, or custom structures. It loads the live structure, rejects unsupported types and invalid properties, resolves label names, and accepts only strict documented API 2.0 blocks. Use create_object_from_url for weblinks. |
| delete_blockA | Delete one existing Capacities block by object ID and block ID. Nested child blocks are deleted with their parent; read structured content first and use only when the deletion is intentional. |
| delete_objectA | Delete a Capacities object. The safe default moves it to trash; permanent deletion requires permanent=true. |
| get_objectA | Read one Capacities object by UUID. Structured JSON is the default and is safe to feed into follow-up edits; request markdown only for a compact, read-only proposal or context view. |
| inspect_spaceA | Inspect the token-bound Capacities space. Without a structure, returns a compact object-type catalog; with a structure ID/name, returns its property definitions, label options, allowed relation types, and collections. Call this before unfamiliar create/update operations. |
| manage_upload_jobA | Manage an in-process Capacities upload job returned by upload_files in background mode. status is immediate, wait blocks up to timeoutSeconds, and cancel aborts pending sessions while preserving already completed media objects. |
| search_objectsA | TITLE-ONLY search for Capacities objects, optionally filtered by discovered structure names or IDs. It never searches body blocks or property values. Returns IDs and titles for get_object or relation fields. |
| update_blockA | Update one existing Capacities block in place using strict structural API 2.0 JSON. Read get_object in structured mode first. The type must match; omitted blocks/columns preserve children, while supplied children replace them. |
| update_objectA | Update an object's title, writable typed properties, or collections after loading its live structure schema. Supplied fields replace that property; omitted fields stay unchanged. Use append_content or update_block for body content. |
| upload_filesA | Upload one or more local files to Capacities as media objects. Streams multipart files without loading them into the model or memory, verifies each completed object with GET, and returns partial results when independent files fail. Use mode=background for long or large batches, then manage_upload_job for status, wait, or cancel. |
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
- 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/Nyrest/capacities-mcp-enhanced'
If you have feedback or need assistance with the MCP directory API, please join our Discord server