bloom-mcp
MCP server for Bloom Growth that allows users to update metrics, check scorecards, and manage rocks directly from Claude.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
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
tbohling15
Source: Glama
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.
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.
get_my_scorecardGet your Bloom Growth scorecard — all measurables with their current week scores and goals.
get_measurableGet details for a specific measurable (metric) by its ID.
list_my_measurablesList all measurables (metrics) assigned to you.
update_scoreUpdate the value of a score by its score ID. Use get_score_history to find score IDs.
update_metric_for_weekPost or update a metric score for a specific week. Provide the measurable ID and week ID. Use get_score_history to find week IDs.
get_score_historyGet the full score history for a measurable. Returns score IDs and week IDs needed for updates.
list_meetingsList all your Level 10 (L10) meetings.
get_meeting_scorecardGet the scorecard for a specific L10 meeting.
get_my_rocksList your current quarterly rocks (goals).
get_meeting_todosList open todos for a specific L10 meeting.
get_todo_notesGet the notes/details text attached to a specific todo. Returns plain text extracted from the todo's notepad.
get_meeting_todos_with_notesList all open todos for a meeting, each enriched with its notes text, and a single top-level link to the meeting's todo list in the current Bloom Growth UI (not the legacy per-todo links). Ideal for posting a todo digest to Slack.
get_rockGet full details for a specific rock by ID, including status, completion percentage, and results so far.
get_user_rocksGet rocks for a specific user by their user ID. Use get_my_rocks first to find user IDs.
update_rockUpdate a rock's status, completion percentage, or title. Status values: 'OnTrack', 'OffTrack', 'Done', 'Unknown'. Completion is 0–100.
get_rock_milestonesList all milestones (plan steps) for a specific rock. Milestones are the bullet points under 'Plan & Milestones' on a rock card.
add_rock_milestoneAdd a new milestone (plan step) to a rock. Milestones appear as bullet points under 'Plan & Milestones' on the rock card.
setup_credentialsSave your Bloom Growth username (email) and password locally so you don't need 1Password or env vars. Credentials are stored in ~/.bloom-mcp/credentials.json with owner-only permissions (chmod 600). Run this once to get started.
check_credentialsShow which credential source is currently active (env vars, local file, or 1Password) and confirm the connection works.
clear_credentialsRemove locally stored Bloom Growth credentials from ~/.bloom-mcp/credentials.json.
BLOOM_MCP_PORTTo use a different port: =9000 BLOOM_MCP_TRANSPORT=http node dist/index.js, then use that port in the address.BLOOM_MCP_TRANSPORTTo use a different port: BLOOM_MCP_PORT=9000 =http node dist/index.js, then use that port in the address.BLOOM_PASSWORDBLOOM_USERNAMETool 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
20/20 tools missing one or more hints — get_my_scorecard (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_measurable (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_my_measurables (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 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.
Destructive tools are labelled
1 tool perform destructive updates without destructiveHint — clear_credentials deletes at line 48 (fs.unlinkSync(CREDENTIALS_FILE))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
14 tools describe read intent but their handlers mutate — get_my_scorecard (line 78: execSync('op read "op://Employee/Bloom Growth/Email"', { encoding: "utf8" })); get_measurable (line 78: execSync('op read "op://Employee/Bloom Growth/Email"', { encoding: "utf8" })); list_my_measurables (line 78: execSync('op read "op://Employee/Bloom Growth/Email"', { encoding: "utf8" }))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Tests exist
No test files found
Add tests that exercise each declared tool.
Shell command execution
2 calls in production code run through a shell (src/index.ts:78, src/index.ts:79)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Tool description accuracy
14 tools have description/behavior mismatches: get_my_scorecard: description implies read-only but handler writes/deletes/executes; get_measurable: description implies read-only but handler writes/deletes/executes; list_my_measurables: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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.
[](https://m8ven.ai/mcp/tbohling15/bloom-mcp)?variant=verified from the URL.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