MCP.Market

Taskboard MCP server

by RefugeSwordPublishing·io.github.RefugeSwordPublishing/taskboard-mcp·v1.0.1
No reviews yet

Persistent task board synced across Claude Code and Claude.ai, backed by Supabase.

C55/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C55/100

full report

Adoption
New

13 downloads/wk

Reviews

Write one

Nobody has reviewed Taskboard yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Taskboard tools (9, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_sectionwrite action

    Create a new section on the TaskBoard. Always tagged source:"claude".

  • add_task

    Add a new task to a section. Use section_id from get_board.

  • ask_claude

    Ask Claude about a task using the user's own Anthropic API key. Requires ANTHROPIC_API_KEY in environment.

  • complete_task

    Mark a task as complete and remove it from the board. Respects user-owned section protection.

  • get_board

    Get all TaskBoard sections, tasks, and pinned reference docs. Call this first in every session to see current state.

  • pin_ref

    Pin a reference document to a section's ref shelf. Use GitHub blob URLs so links open on mobile.

  • remove_refwrite action

    Remove a pinned reference doc from a section.

  • remove_sectionwrite action

    Delete an entire section and all its tasks. User-owned sections are protected unless override is set.

  • remove_taskwrite action

    Remove a task without marking it complete (cancelled, duplicate). Respects user-owned section protection.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan8 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancerepository not readable: repo not found3/15
  • Maintainer identityno repository or website to verify2/10
Overall 55/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Taskboard compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
55/100
higher than 9% of 802 Databases servers
Tools
9
the typical Databases server has 8
Tools that change things
44%
typical: 10%. Fewer write tools means less an agent can break
Downloads a week
13
more than 3% of 328 Databases servers with a package

What its tools let an agent do: 4 read · 2 create · 3 delete

Install Taskboard in Claude Code, Cursor or VS Code

Runs npx -y @refugeandsword/taskboard-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add taskboard-mcp -- npx -y @refugeandsword/taskboard-mcp
Add to Cursor

Taskboard: common questions

Is Taskboard MCP server safe?
With care: it is graded C, so read the findings first (55/100). Read the Taskboard safety report
How do I install Taskboard?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Taskboard need an API key?
Yes. The registry entry asks for SUPABASE_ANON_KEY, ANTHROPIC_API_KEY.
Is Taskboard maintained?
The latest release is v1.0.1.
What can I use instead of Taskboard?
Servers from other publishers that do the same job: hmem — Humanlike Memory for AI Agents MCP server, Supabase MCP server and Ekwo OS — open source accounting: ledger, invoices and VAT on your own Supabase or Postgres MCP server.
How does Taskboard compare with other Databases MCP servers?
safety score 55/100 (higher than 9% of 802 Databases servers); tools 9 (the typical Databases server has 8); tools that change things 44% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Taskboard

Same job from other publishers: the closest match first, then the best rated.