kanban-lite (borgius/kanban-lite) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 67 tools. No publisher has claimed this listing.

D
Emerging
54/100

kanban-lite

A kanban board for your codebase. Features stored as markdown.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

borgius

Source: Glama · also listed on github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 6 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: KANBAN_LITE_TOKEN, KANBAN_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes67 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

list_boards

List all kanban boards.

create_board

Create a new kanban board.

get_board

Get details of a specific board.

delete_board

Delete an empty kanban board.

transfer_card

Transfer a card from one board to another.

list_board_actions

List all named actions defined on a board.

add_board_action

Add or update a named action on a board. Actions appear in the board toolbar and fire webhooks when triggered.

remove_board_action

Remove a named action from a board.

trigger_board_action

Fire a named board action, emitting a board.action webhook event.

list_board_logs

List all board-level log entries from the board.log file.

add_board_log

Append a new entry to the board-level log file.

clear_board_logs

Clear all board-level log entries by deleting the board.log file.

list_cards

List all kanban cards. Optionally filter by status, priority, assignee, label, searchQuery, or metadata fields. Fuzzy search also applies to metadata values, while metaFilter remains available for structured field-specific searches.

get_card

Get full details of a specific kanban card by ID. Supports partial ID matching.

get_active_card

Get the card currently marked as active/open in the workspace. Returns null when no card is active.

create_card

Create a new kanban card. Returns the created card. Supports form attachments and persisted per-form data for form-aware workflows.

update_card

Update fields of an existing kanban card. Only specified fields are changed. Supports replacing attached forms and persisted per-form data.

submit_card_form

Submit a named/resolved form for a card using the SDK-owned validation and persistence contract. Returns the canonical persisted payload and form/card context.

move_card

Move a kanban card to a different status column.

delete_card

Soft-delete a kanban card (moves to deleted status). Use permanent_delete_card to remove from disk.

permanent_delete_card

Permanently delete a kanban card from disk. This cannot be undone.

trigger_action

Trigger a named action on a card. The action name must match one of the card's configured actions. Emits a card.action.triggered event delivered to registered webhooks.

list_attachments

List all attachments on a kanban card.

add_attachment

Add a file attachment to a kanban card. Copies the file to the card directory.

remove_attachment

Remove an attachment from a kanban card. Only removes the reference, not the file.

list_comments

List all comments on a kanban card.

add_comment

Add a comment to a kanban card.

stream_comment

Add a comment to a kanban card from a streaming text source. Provide the full content string; it will be written via the streaming path so connected webview clients see it arrive incrementally.

update_comment

Update the content of a comment on a kanban card.

delete_comment

Delete a comment from a kanban card.

list_logs

List all log entries for a kanban card. Logs are stored in a dedicated .log file.

add_log

Add a log entry to a kanban card. The log is appended to the card's .log file.

clear_logs

Clear all log entries for a kanban card by deleting the .log file. New logs will recreate it.

list_columns

List all kanban board columns.

add_column

Add a new column to the kanban board.

update_column

Update an existing kanban board column.

remove_column

Remove a column from the kanban board. Fails if any cards are in the column.

reorder_columns

Reorder columns on a board by providing the full ordered list of column IDs.

set_minimized_columns

Persist the minimized column IDs for a board to the config file. Pass an empty array to clear all minimized columns.

cleanup_column

Move all cards in a column to the deleted (soft-delete) column. The column itself is kept.

list_labels

List all label definitions with colors and groups

set_label

Create or update a label definition

rename_label

Rename a label (cascades to all cards)

delete_label

Remove a label definition and remove it from all cards

get_settings

Get the current kanban board display settings.

update_settings

Update kanban board display settings. Only specified fields are changed.

list_available_events

List discoverable SDK events, including built-in before/after events and any plugin-declared additions. Supports optional phase and wildcard mask filtering.

get_auth_status

Get the active auth providers and host token-source diagnostics for the MCP server.

get_workspace_info

Get the workspace root path, cards directory, active storage engine, and configured-versus-effective config.storage status.

get_storage_status

Get the current storage engine type plus configured-versus-effective config.storage status, including explicit failure or degraded state when present.

migrate_to_sqlite

Migrate all card data from the current markdown storage to a SQLite database. Updates .kanban.json automatically.

migrate_to_markdown

Migrate all card data from SQLite back to individual markdown files. Updates .kanban.json automatically.

get_card_state_status

Get the active card-state provider status for this workspace.

get_card_state

Get the side-effect-free unread/open summary for one card. Supports partial ID matching and never mutates unread state implicitly.

open_card

Persist an explicit actor-scoped open mutation through the shared SDK card-state APIs. This acknowledges unread activity and records open-card state without changing active-card UI state.

read_card

Persist an explicit actor-scoped unread acknowledgement through the shared SDK card-state APIs without changing open-card state.

list_plugin_settings

List the capability-grouped plugin provider inventory for this workspace, including selected config.storage resolution state when present.

get_plugin_settings

Read the redacted provider state for one capability/provider pair, including configured-versus-effective config.storage resolution details when applicable.

select_plugin_settings_provider

Persist the selected provider for a plugin capability and return the redacted provider read model. Rejected config.storage topology mutations are surfaced as explicit errors.

update_plugin_settings_options

Persist provider options for a capability/provider pair and return the redacted provider read model, preserving explicit config.storage error/degraded state when reported by the SDK.

install_plugin_settings_package

Install a supported plugin package with the shared SDK guardrails and return the redacted install result.

list_card_checklist_items

List the checklist items for a card, including expectedRaw values for optimistic concurrency.

add_card_checklist_item

Add a checklist item to a card and return the caller-scoped checklist payload. expectedToken is required to avoid lost concurrent appends.

edit_card_checklist_item

Edit an existing checklist item. modifiedAt is recommended to avoid stale overwrites.

delete_card_checklist_item

Delete an existing checklist item. modifiedAt is recommended to avoid stale deletes.

check_card_checklist_item

Mark a checklist item as checked. modifiedAt is recommended to avoid stale writes.

uncheck_card_checklist_item

Mark a checklist item as unchecked. modifiedAt is recommended to avoid stale writes.

// known CVEs in dependencies6 high24 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@hono/node-server@1.19.9GHSA-wc8c-qw6v-h7f6

@hono/node-server has authorization bypass for protected static paths via encoded slashes in Serve Static Middleware

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highhono@4.12.0GHSA-88fw-hqm2-52qc

hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configKANBAN_CONFIG
configKANBAN_DIR
configKANBAN_FEATURES_DIR
🔐 secretKANBAN_LITE_TOKEN
🔐 secretKANBAN_TOKEN
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

67/67 tools missing one or more hints — list_boards (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_board (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_board (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +64 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

25/67 tools referenced in tests (37%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 6 high severity in production deps — @hono/node-server@1.19.9 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dependency freshness

1/33 production deps stale: eventemitter2@2022-09-12 (4y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/borgius/kanban-lite)](https://m8ven.ai/mcp/borgius/kanban-lite)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 6254ddde8b0d49e5915b859310602744ecad61b3
code hash: 424bc1cf079d224b0ddf2a35999fe07636a3019c2ad16f9b528175d17935e4c6
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client