TanaSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!IMPORTANT] This project is no longer actively maintained. I've moved on from Tana and no longer use the software, so I'm not in a position to keep this MCP server current or provide ongoing support. The repository remains available as a reference, and anyone who finds it useful is encouraged to fork it and continue development.
A Model Context Protocol (MCP) server that connects to Tana's Input API, enabling AI assistants to create and manipulate data in your Tana workspace.
Table of Contents
- Features
- Prerequisites
- Getting Your Tana API Token
- Installation
- Raycast
- Claude Code (CLI)
- Claude Desktop
- Other MCP Clients
- Configuration Options
- Usage
- Available Tools
- Example Prompts
- Text Formatting
- API Limitations
- Development
- Troubleshooting
- License
Features
Tools (12 available)
2083742e388aOBSERVED · 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 tana-mcp --env TANA_API_TOKEN=${TANA_API_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"tana-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"TANA_API_TOKEN": "${TANA_API_TOKEN}"
}
}
}
}Exposed tools (13)
1 read · 12 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
2023-12-25 | read | Christmas Day |
add_field_value | write | |
create_checkbox_node | write | |
create_date_node | write | |
create_field | write | |
create_file_node | write | |
create_formatted_node | write | |
create_node_structure | write | |
create_plain_node | write | |
create_reference_node | write | |
create_supertag | write | |
create_url_node | write | |
set_node_name | write |
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 | PASS |
| 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 (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, axios, typescript, zod, @types/node, ts-node
Gates applied: no_behavioural_pass.
2083742e388afull audit observations/trust-audit/mcp-server/tim-mcdonnell__tana.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 | 2083742e388a | SAFE | B | 89 | first audit |
Questions
What tools does Tana expose?
13 in total: 1 read-only, 12 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Tana 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 Tana need?
It reads TANA_API_TOKEN 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 Tana run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as tana-mcp at 2.0.0.
How current is this page?
The grade is for one exact copy of the source (2083742e388a), read on 2026-10-08. The repository is watched and re-audited when it changes.