CapacitiesSAFE
Capacities×MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An enhanced MCP (Model Context Protocol) server for Capacities, providing seamless integration with your knowledge management system.
Note: This is a fork of jemgold/capacities-mcp with additional features and fixes.
What's Different from the Original
New Tool: capacities_read_object_content
Retrieve the full content of any Capacities object by its ID:
- Tries undocumented API endpoints first for direct retrieval
- Falls back to search API aggregation when direct access unavailable
- Provides title parameter to improve search accuracy
Features
This MCP server provides access to all current Capacities API endpoints:
- List Spaces - Get all your personal spaces
- Space Information - Retrieve detailed space structures and collections
- Search Content - Search across spaces with advanced filtering
- Read Object Content - Retrieve full note content by object ID
- Save Weblinks - Save URLs to your spaces with metadata
- Daily Notes - Add content to your daily notes
Installation
For Claude Desktop (macOS)
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"capacities": {
"command": "npx",
"args": ["-y", "capacities-mcp-plus"],
"env": {
"CAPACITIES_APd4f83afcad42OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add capacities-mcp-plus --env CAPACITIES_API_KEY=${CAPACITIES_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"capacities-mcp-plus": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"CAPACITIES_API_KEY": "${CAPACITIES_API_KEY}"
}
}
}
}Exposed tools (6)
4 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
capacities_get_space_info | read | Get information about a Capacities space |
capacities_list_spaces | read | Get a list of all personal spaces in Capacities |
capacities_read_object_content | read | Retrieve the full content of a Capacities object by its ID. Optionally provide a title or search term to improve results. This tries undocumented endpoints first, then falls back to search API aggregation. |
capacities_save_to_daily_note | write | Add markdown text to today |
capacities_save_weblink | write | Save a web link to a Capacities space with optional title and tags |
capacities_search | read | Search for content across Capacities spaces with optional filtering |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
bun.lockb
@modelcontextprotocol/sdk, zod, @biomejs/biome, @tsconfig/node22, @types/node, jiti, semantic-release, tsx
Gates applied: no_behavioural_pass.
d4f83afcad42full audit observations/trust-audit/mcp-server/jem-computer__capacities.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | d4f83afcad42 | SAFE | B | 89 | first audit |
Questions
What is the Capacities MCP server?
Capacities×MCP
What tools does Capacities expose?
6 in total: 4 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Capacities safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Capacities need?
It reads CAPACITIES_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Capacities run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as capacities-mcp-plus at 1.2.0.
How current is this page?
The grade is for one exact copy of the source (d4f83afcad42), read on 2026-10-08. The repository is watched and re-audited when it changes.