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.

Kangram

REMOTE · KANGRAM.APP

Task & board management for AI agents + humans. Kanban, comments, digests via MCP.

Available components

+32 this week 65 Trust /100

Last scanned (5 hours ago)

Scores higher than 47% of remote servers

Reachable. Last reached 18 Oct 2026.

Category Project Management

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security57
Transport & Reachability100
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 5797 tokens (~95/item across 61 items; 61 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management10
  • Stability observed for 3 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 Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 9 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_task" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 61 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
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.

  • 17 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Oct 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 15 Oct 26 +28
    • Authorization: pass → unverified ▼ security
    • Transport: unverified → pass ▲ security
    • Injection markers: unverified → pass ▲ security
    • First check of Judged manipulation: pass security
    • MCP protocol: unverified → pass ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Schema quality: excellent functional
    • First check of Destructive annotations: 0 functional
    • First check of Schema quality: pass functional
    • First check of Tool coverage: 100 functional
  • 13 Oct 26 +3
    • Authorization: fail → pass ▲ security
    • First check of Authorization: partial security
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 19 Aug 26 0

    First indexed and scored.

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 18 Oct 2026 · Probed https://kangram.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=kangram.app CN=WE1,O=Google Trust Services,C=US 5 Sept 2026 4 Dec 2026 ECDSA 256 ECDSA-SHA256 53e77fad7680b98c0ea9b6f25502e446
SANs: kangram.app, *.kangram.app
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of kangram.app. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
kangram.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://kangram.app/mcp Verified 200
http (plaintext) http://kangram.app/mcp HTTPS enforced 301 https://kangram.app/mcp
MCP tools · 61 exposed · ~5,797 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
save_session_handoff ~223

Save a session handoff — a durable note on the board recording where the work stands: what was done, what is next, what is blocked, and key links (PRs, issues, branches). Call this at the END of a working session so the next session (possibly a brand-new chat) can pick up exactly where you left off. Use this when the user says 'remember where we left off', 'save our progress', 'save the session state', or 'don't lose this context'. `summary` must be YOUR OWN concise authored recap — never a transcript or list of raw messages.

NameTypeReqDescription
board_idintegeryesBoard ID the handoff belongs to.
links––Optional references — PR/issue URLs, branch names, doc links (e.g. ['https://github.com/o/r/pull/12', 'feat/auth-refactor']). Max 25 single-line items.
summarystringyesYour authored recap: done / next / blocked. One concise string (max 20000 chars) — not a transcript.

No output schema declared.

No examples provided.

search_tasks ~164

Use this to find tasks by text, assignee, status, priority, or attention category across all your accessible boards. All filters are optional — combine them to narrow results. Returns up to 50 tasks ordered by last updated.

NameTypeReqDescription
assignee_idinteger–Filter by assignee user ID.
attentionstring–Filter by attention category: overdue, due_soon, blocked, stale, unassigned.
board_idinteger–Scope to a specific board ID.
prioritystring–Filter by priority: critical, major, normal, or low.
querystring–Search query text (matches task title and description).
statusstring–Filter by completion status: 'open' (not done) or 'done'.

No output schema declared.

No examples provided.

set_board_setting ~154

Use this command to change a board setting. The value is a string coerced to the setting's type server-side (booleans accept on/off, true/false, 1/0, yes/no). Use get_board_settings_schema to discover available keys and types. Example: set autoAddAssignees to "off" to require explicit /addmember on task assignment.

NameTypeReqDescription
board_idintegeryesBoard ID to configure.
keystringyesSetting key (e.g. "autoAddAssignees").
valuestringyesNew value as a string (coerced to the setting's type). Booleans: on/off, true/false, 1/0.

No output schema declared.

No examples provided.

transfer_board_ownership ~145

Transfer ownership of a board from the current owner to an existing board member (admin or user role). The current owner is demoted to the specified role (admin by default). Only the current board owner can initiate a transfer. The target must already be a board member — invite them first if needed. This is an irreversible high-impact operation.

NameTypeReqDescription
board_idintegeryesBoard ID to transfer ownership of.
demote_current_owner_tostring–Role to assign to the current owner after the transfer. Defaults to 'admin'.
to_user_idintegeryesUser ID of the new owner. Must already be a board member (admin or user role).

No output schema declared.

No examples provided.

transition_task_status ~58

Use this for explicit status moves while keeping other fields unchanged.

NameTypeReqDescription
board_idintegeryesBoard ID where the task belongs.
statusstringyesTarget status name.
task_numberintegeryesTask number in board scope.

No output schema declared.

No examples provided.

update_board ~230

Use this to edit board metadata (title, code) and/or the board-level agent prompt. The prompt is the markdown instructions an agent reads when operating on this board (stored as the root file "AGENTS.md"). Pass only the fields you want to change; omitted fields are left untouched. Pass an empty string as prompt to clear the prompt.

NameTypeReqDescription
board_idintegeryesBoard ID to update.
codestring–New board code (3 letters or digits A-Z/0-9, unique within the namespace). Omit to leave unchanged.
promptstring–Markdown agent prompt for this board (stored as the root "AGENTS.md" file). Omit to leave unchanged; pass an empty string to clear. May include YAML frontmatter.
titlestring–New board title. Omit to leave unchanged.
visibilitystring–Set board visibility. 'private' (default) = members-only; 'public' = anyone with the link can view the board read-only (no account required). Owner/admin only. Omit to leave unchanged.

No output schema declared.

No examples provided.

update_board_file ~146

Upsert a named markdown file on a board. In v1 the conventional name is "AGENTS.md" (the root prompt). Omit content (or pass empty) to clear a file's body. Future versions will support multiple named files; this command is the low-level writer beneath update_board's prompt option.

NameTypeReqDescription
board_idintegeryesBoard ID to write the file on.
contentstring–Markdown content. Omit or pass empty to clear the file body.
formatstring–File format. Defaults to "markdown".
namestringyesFile name (path-like identifier). Use "AGENTS.md" for the root prompt.

No output schema declared.

No examples provided.

update_checklist_item ~67

Use this to update a checklist item's title or done status. Provide item_id and fields to update.

NameTypeReqDescription
doneboolean–Set done status (true/false).
item_idintegeryesChecklist item ID.
titlestring–New title for the item.

No output schema declared.

No examples provided.

update_member_role ~86

Use this command to change an existing board member's role. Owner/admin only. Cannot target the board owner or promote anyone to owner.

NameTypeReqDescription
board_idintegeryesBoard ID where the member belongs.
rolestringyesNew role to assign (admin or user). Cannot assign owner.
user_idintegeryesUser ID of the member whose role to change.

No output schema declared.

No examples provided.

update_status ~103

Update status by statusId or by boardId+code.

NameTypeReqDescription
board_idinteger–Board ID for board+code lookup.
codestring–Existing status code for board+code lookup.
colorstring–New hex color.
indexinteger–New sort index.
namestring–New display name.
new_codestring–New machine code value.
status_idinteger–Target status ID.

No output schema declared.

No examples provided.

update_task ~135

Use this to edit task title/description/deadline/tags/assignee/status.

NameTypeReqDescription
assigneestring–Assign by username (without @).
board_idintegeryesBoard ID where the task belongs.
deadlinestring–New deadline string.
descriptionstring–New description.
prioritystring–Set priority: critical, major, normal, or low.
statusstring–Set status by name.
tagsarray–Replace task tags list.
task_numberintegeryesTask number in board scope.
titlestring–New title.

No output schema declared.

No examples provided.

Install

How do I install the Kangram MCP server?

Kangram is a hosted endpoint at https://kangram.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · kangram.app

# add to Claude Code
claude mcp add --transport http app-kangram-kangram 'https://kangram.app/mcp'
Common questions

What is the Kangram MCP server?

Kangram is an MCP server listed in the public MCP registry as app.kangram/kangram. Task & board management for AI agents + humans. Kanban, comments, digests via MCP. This page covers its hosted endpoint (https://kangram.app/mcp).

Is the Kangram MCP server safe to use?

Kangram scores 65 out of 100 on VerifyMCP. 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 Kangram MCP server expose?

Kangram exposes 61 tools: list_boards, create_board, update_board, get_board_by_namespace, archive_board, and 56 more. Their descriptions and schemas cost roughly 5,797 tokens of context every time the server is loaded.

Does the Kangram MCP server require authentication?

No. We connected to Kangram without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Kangram MCP server still maintained?

Kangram is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.