Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

TabTree

NPM · TABTREE-MCP · SCANNED SEP 24

Turn conversations into mind maps and whiteboards — in your TabTree account, or local files.

Available components

+3 this week 78 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency32
Schema Quality & AI Usability74
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 938 tokens (~156/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management73
  • Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the TabTree MCP server?

TabTree runs locally as an npm package, launched with npx -y tabtree-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · tabtree-mcp

# add to Claude Code
claude mcp add app-tabtree-tabtree -- npx -y tabtree-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "app-tabtree-tabtree": {
      "command": "npx",
      "args": [
        "-y",
        "tabtree-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "app-tabtree-tabtree": {
      "command": "npx",
      "args": [
        "-y",
        "tabtree-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add app-tabtree-tabtree -- npx -y tabtree-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-tabtree-tabtree": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tabtree-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add app-tabtree-tabtree --command npx --arg -y --arg tabtree-mcp
# ~/.hermes/config.yaml
mcp_servers:
  app-tabtree-tabtree:
    command: "npx"
    args: ["-y", "tabtree-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "app-tabtree-tabtree": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "tabtree-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add app-tabtree-tabtree -t stdio -c npx -a -y tabtree-mcp
// mcp.json
{
  "mcpServers": {
    "app-tabtree-tabtree": {
      "command": "npx",
      "args": [
        "-y",
        "tabtree-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1
    • Security disclosure: unverified → fail ▼ functional
  • 13 Sept 26 +1
    • Security disclosure: fail → unverified ▼ functional
  • 11 Sept 26 +12
    • Known CVEs: unverified → pass ▲ security
    • Dependency health: unverified → pass ▲ functional
  • 10 Sept 26 −11
    • Stability: 0.23 → unverified ▼ security
    • Known CVEs: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Dependency health: pass → unverified ▼ functional
    • First check of Schema quality: unverified functional
    • Package version: 1.2.0 → 1.2.1 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Analysed npm/tabtree-mcp@1.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 6 exposed · ~938 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_board ~284

Creates a NEW TabTree board (whiteboard): shapes (rect, ellipse, diamond, text, sticky) and arrow connections that stay anchored to the shapes in the app. With no x/y coordinates, layout is automatic by level (the connections define the hierarchy, left to right). Good for a diagram, a flow, a brainstorm. In a flowchart use ellipse for start/end, rect for a step, and diamond for a decision — its text should read as a closed question with exactly two ways out. FIT THE TEXT TO THE BOX. A box shows roughly (w−24)/7 characters per line and (h−10)/20 lines, and every blank line costs a full line. Write captions, not paragraphs: when filling a canvas template (Business Model Canvas, Lean Canvas, SWOT…), the shipped templates use 70–110 characters per block, and that is what looks composed. Longer text is shrunk to fit — nothing ever spills out — but past ~11px it stops being readable and the response will warn you.

NameTypeReqDescription
connectionsarray–Arrows anchored between elements (by id)
elementsarrayyesBoard elements
folderstring–Optional TabTree subfolder
namestringyesName of the board
styleobject–Optional look of the document. Omit it for the default.

No output schema declared.

No examples provided.

create_mindmap ~301

Creates a NEW TabTree mind map from a markdown outline (#/## headings, bullet lists indented by 2 spaces, [x]/[ ] checkboxes, [title](url) links, and " @a:<id>" / " @e:<emoji>" at the end of a line for an illustration). The first top-level line becomes the centre. Writes a .tabtree file into the backup folder; the user pulls it into the app from the 🛟 menu.

NameTypeReqDescription
folderstring–Optional TabTree subfolder (e.g. "From Claude")
markdownstringyesMarkdown outline (headings and/or bullet list). End any line with " @a:<id>" to give that node a built-in illustration, or " @e:<emoji>" for one large emoji — e.g. "Launch @a:rocket". Ids: person, te…
namestringyesName of the map
styleobject–Optional look of the document. Omit it for the default.

No output schema declared.

No examples provided.

list_maps ~31

Lists every mind map and board in the TabTree library (name, type, folder, size, last modified).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

propose_changes ~208

Proposes changes to an EXISTING mind map: add branches, rename a node, write a note, tick a task, remove a branch, illustrate a node — or, with op "persona", re-cast a WORK MAP canvas from a finished interview (the JSON block of the « ma cartographie du travail » skill). Nothing is applied — the proposal appears in TabTree as a banner on that map, the user reviews it change by change and picks what to keep (and can undo with Cmd+Z afterwards). Name each target node by its exact text, or by a path "Ancestor > Node" when the same wording appears twice. Read the map first so the wording matches.

NameTypeReqDescription
changesarrayyesThe proposed changes, applied in order
filestringyesThe map to change — a file name (or map name) from list_maps
notestring–One line telling the user what this proposal does and why. Shown above the changes.

No output schema declared.

No examples provided.

read_map ~70

Reads one TabTree map. A mind map comes back as a markdown outline; a board as a list of elements and connections. `file` is a file name (or a map name) returned by list_maps.

NameTypeReqDescription
filestringyesThe .tabtree file name (or the map name)

No output schema declared.

No examples provided.

search_maps ~44

Searches text across the whole TabTree library — map names, nodes, notes, shapes, sticky notes. Case-insensitive.

NameTypeReqDescription
querystringyesText to search for

No output schema declared.

No examples provided.

Common questions

What is the TabTree MCP server?

TabTree is an MCP server listed in the public MCP registry as app.tabtree/tabtree. Turn conversations into mind maps and whiteboards, in your TabTree account, or local files. This page covers its npm package (tabtree-mcp).

Is the TabTree MCP server safe to use?

TabTree scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the TabTree MCP server expose?

TabTree exposes 6 tools: list_maps, read_map, search_maps, create_mindmap, create_board, propose_changes. Their descriptions and schemas cost roughly 938 tokens of context every time the server is loaded.

Is the TabTree MCP server still maintained?

TabTree is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.