"QA review sentinel test marker" matching MCP tools:

• delete_lab_resultA

  Wellness ProjectA

  Permanently delete one or more lab results. Use when the user explicitly asks to remove or delete a logged lab result. Never guess a selector. SELECTOR, pass exactly one of id, date, date+marker, or draw_id: - id: deletes a single marker's row. - draw_id: deletes every result sharing that draw_id at once, unambiguous by construction. Irreversible. - date (optionally narrowed by panel_name): deletes every result from that draw at once, but ONLY when exactly one draw exists on that date — see AMBIGUITY below. Irreversible and can remove many rows in one call. Confirm with the user before a date-scoped delete, especially one not narrowed by panel_name or marker. - date + marker (a marker-name substring, case-insensitive, optionally narrowed by panel_name): resolves to and deletes one marker's row, same as id. Errors with candidate IDs if more than one marker on that date matches. AMBIGUITY: a bare date (optionally + panel_name) selector is rejected, with nothing deleted, if it would match more than one physical draw — an explicit draw_id from one source plus legacy rows with none, two distinct draw_ids, or two differently-named legacy sources on the same day. The error names every draw found; retry with draw_id, marker, or a narrower panel_name.

  Connector

  Destructive

  OAuth

• log_lab_resultsA

  Wellness ProjectA

  Log one or more blood test or biomarker results. use: requested logging/import of lab values or a concrete result to record. Review/interpretation alone: no write. GLUCOSE ROUTING: use this tool for glucose only when it is an actual lab/blood-draw result or part of a reported lab panel. Finger-stick, CGM, home meter, wearable, Apple Health, or Health Connect glucose — including a manual correction to daily glucose — belongs in log_wearable as blood_glucose_mg_dl, not here. REQUIRED WORKFLOW: 1) call list_lab_markers for canonical names and LOINC codes. 2) for each marker the user provides, find the best match and use its canonical marker_name and loinc_code. 3) if no match exists, use the name as stated and omit loinc_code. If the user says they have lab results but hasn't shared them, prompt: "You can paste the text from your lab report PDF, or upload a photo of the results page — I'll parse all the values at once." collection_date: report or explicit user context; missing: ask, never substitute report_date or today. infer: panel_name from matched marker or context. extract: flag (H/L/HH/LL/A), ref_range_low/high and lab_name only when reported. FASTING: fasting_status is only 'fasting' or 'non_fasting' when the user explicitly states it ("I fasted for this", "hadn't eaten"). Never infer it from time of day, a meal mention in notes, or the draw being in the morning — omit the field (leaves it unknown) whenever it wasn't stated. report_date (when the lab reported results, if given separately from the collection date) and draw_id (only when the user is adding a marker to a draw already logged in this conversation) are also optional, omit otherwise. Submit all markers from a single lab visit in one call.

  ConnectorOAuth

• add_changelog_entryA

  cortexpadA

  Add a short, dated changelog entry to a note — structured evidence of a change (e.g. "Bumped reply target 3-5 → 8-10"), separate from and never touching the note body by default. Purely additive: does not overwrite or clobber content. Two ways to use it: (1) create a NEW numbered entry — if `anchor` is given (exact or substring text of an existing line), a small "((n))" marker pointing to the new entry is appended to that line, failing if `anchor` doesn't match any line (call get_note first if unsure of the exact text); without `anchor` the entry is note-wide with no inline marker. (2) append to an EXISTING entry via `appendTo: n` (e.g. 3 for an existing "((3))" marker) — adds another dated comment/update under that same marker without creating a new marker or number; fails if entry `n` doesn't exist yet. `appendTo` and `anchor` are mutually exclusive — `anchor` is ignored when `appendTo` is set. Use `section` (e.g. "update", "note") to label what kind of entry this is when a marker accumulates several over time — the UI groups/filters by section. Use this instead of update_note/append_to_note when recording a decision or change without altering the visible note text. Capped to the most recent 20 entries total across all markers.

  ConnectorAPI key

• send_mission_instructionA

  SHIPA

  Tell a mission what to change. Use kind='follow_up' (the default) to ask for a change: the instruction reaches the agents AND dispatches the builder against the mission's open pull request, overriding cached review and QA verdicts. Use kind='note' to record context for whatever runs next without starting any work. A restart is a different thing: it re-evaluates an unchanged pull request against its cached verdicts, and so changes nothing. Returns a receipt saying what was recorded and what it will cause. This tool calls the SHIP API, documented at https://letsship.ai/docs/api. Requires the missions:write token scope.

  ConnectorNo auth

• request_secretA

  AnkraB

  Ask the person for a secret only they have - an API token, a password, a licence key - without the value ever entering this conversation. If the organisation already stores a secret under the name, it answers status 'stored' with its sentinel. Otherwise it answers status 'waiting_for_person' with a link to the organisation's secrets page: give the person the link, ask them to store the secret there under exactly that name, and when they say it is done call request_secret again with the same name to get the sentinel. Never ask for, accept or repeat a secret value in the conversation; for a value nobody needs to know (a database password, a signing key) use create_secret instead. Read-only.

  ConnectorOAuth

• diff_mappingsA

  IA-QA — 152 QA & Dev Tools for AI AgentsA

  Diff a baseline page mapping against a current one and return a CI-style verdict: PASS / FIX / BLOCK, plus per-element drift (ok, renamed, healable, ambiguous, lost, added, rebound). Pure and deterministic — provide two mappings as JSON with "elements" arrays of {role, name, selector, context?}. Use the companion @ia-qa/self-healing package (npm install -g @ia-qa/self-healing) to capture mappings from your app via its local MCP server ia-qa-heal-mcp, or paste the snippet from ia-qa.com/devtools/selector-drift into your browser console.

  ConnectorNo auth

• remove_changelog_entryA

  cortexpadA

  Permanently remove a single changelog entry (e.g. a test/junk entry added by mistake). Strips the trailing "((n))" marker from content if the removed entry itself carried it, and decrements the lifetime section counter so a removed entry stops inflating it. A marker number is NOT a unique entry id -- appendTo lets many entries share one n as a running thread. If more than one entry shares n, this fails and lists each entry's `at` timestamp; pass the specific one you mean as `at` to remove only that entry, not the whole thread. Call get_note first if unsure which entries share a marker.

  ConnectorAPI key

• seo_rows_listA

  pSEO EngineA

  Returns a page of rows (individual generated pages) with slug, target keyword and status. Statuses are PENDING (no content yet), GENERATING, GENERATED (draft), REVIEWED (approved), PUBLISHED (live), FAILED, FLAGGED_DUPLICATE. Content bodies are NOT included — this is a listing, not an export. Use sort:'risk' to get the review queue ordered by risk score (duplicates and pages with QA findings first) so a human reviews the riskiest pages before bulk-approving the safe ones. Costs 3c per call.

  ConnectorNo auth

• get_monitoring_planA

  financeB

  Get the user's agent monitoring plan — what the sentinel watches for them (bill coverage, low balance, idle surplus, cashflow shortfall, anomalies) plus the check-in cadence. While the plan is DRAFT (not yet approved/activated), the sentinel does nothing — activation is the user's opt-in to hands-off monitoring. Args: refresh_snapshot: Also run a fresh survey of the user's finances (upcoming bills, income cadence, available funds) and include it as "snapshot" — useful when helping the user set up or review their plan. Returns: {plan: {...}, snapshot?: {...}}

  ConnectorAPI key

• show_personality_testA

  Zovo Big Five TestA

  Use this when the user wants to take a personality test, a Big Five (five-factor, OCEAN) test, or a personality test for self-reflection, students, teens or couples. Shows the 50 public-domain IPIP Big-Five Factor Marker items in an interactive widget (one at a time, progress bar, back button); answers stay in the widget until the user submits, then they are scored with calculate_personality_scores. Also returns the item list and a browser link to take the same test. Does not score anything by itself. Do not use for MBTI/16-type, DISC or Enneagram tests, or to screen job candidates.

  ConnectorNo auth

• create_secretA

  AnkraB

  Create an organisation secret whose value Ankra generates - a random value nobody sees, you included - for a credential that only has to match between the parts that use it (a database password, a signing key, a shared token). Answers with the secret's ${SECRET_SLOT:<id>} sentinel; put the sentinel where the value belongs and Ankra resolves and seals it at deploy. The secret has no expiry: it stays until a person deletes it. It never takes a value: for a secret the person already has, use request_secret.

  ConnectorOAuth

• stride.update_story_statusA

  Stride — AI software delivery platformA

  Transition a story's status with an optional comment. `status` accepts a category (TODO / IN_PROGRESS / IN_REVIEW / DONE — always valid) OR the exact name of a board column from stride.list_workflow_stages (a project may have custom columns like "Code Review" or "QA"). Identify the story by ticket key (e.g. "ORB-526") or UUID. An unrecognised status returns an error listing the project's columns. Rejected with a conflict error if a human edited the story after your last read; call stride.get_story first, or pass force:true (only with the human's explicit approval) to overwrite their edit.

  Connector

  Destructive

  OAuth

• waveguard_scanA

  WaveGuardB

  Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot, Financial APIs, GitHub, NPM, or any source that returns rows of JSON. Fully stateless: send known-good rows as training and suspect rows as test in ONE call. Returns per-row anomaly scores, confidence levels, and the top features explaining WHY each row was flagged. Typical workflow: (1) Pull data from another tool (e.g. Google Sheets, Supabase query, HubSpot deals). (2) Pass the first N rows as training (normal baseline). (3) Pass remaining or new rows as test. (4) Report which rows are anomalous and why. Works on JSON objects, numbers, text, arrays. No separate training step required. Examples: - Spreadsheet QA: Pull 500 sales rows from Sheets → train on first 400 → test last 100 → flag outlier entries - Financial screening: Get ratios for 50 stocks from a financial API → find anomalous ones - CRM hygiene: Pull HubSpot deals → flag deals with unusual discount/value patterns - Dependency audit: Get NPM package metrics → flag packages with anomalous quality scores - Commit review: Pull GitHub commit metadata → flag unusual commit patterns

  ConnectorNo auth

• get_testing_guidelinesA

  IA-QA — 152 QA & Dev Tools for AI AgentsA

  Query the IA-QA methodology knowledge base. Returns structured testing guidelines, assertion strategies, thresholds, best practices, and relevant MCP tools for a given topic. Call without a topic to list all available topics. Topics: llm-unit-testing, rag-pipeline, prompt-stability, prompt-ab-testing, embedding-quality, eval-framework, semantic-testing, auto-testing, security, api-testing, ci-cd, multimodal, llm-data-security, agent-observability, pro-tips, learning-paths, golden-dataset, selector-drift, qa-recipes, playbooks. Not sure where to start testing an LLM, RAG pipeline or agent? Call without a topic (or with "start-here"): it maps what you are testing to the tools to call and the output field to gate CI on. A plain question such as "how do I test my RAG" also resolves to the right topic.

  ConnectorNo auth

• waveguard_scanA

  WaveGuardA

  Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot, Financial APIs, GitHub, NPM, or any source that returns rows of JSON. Fully stateless: send known-good rows as training and suspect rows as test in ONE call. Returns per-row anomaly scores, confidence levels, and the top features explaining WHY each row was flagged. Typical workflow: (1) Pull data from another tool (e.g. Google Sheets, Supabase query, HubSpot deals). (2) Pass the first N rows as training (normal baseline). (3) Pass remaining or new rows as test. (4) Report which rows are anomalous and why. Works on JSON objects, numbers, text, arrays. No separate training step required. Examples: - Spreadsheet QA: Pull 500 sales rows from Sheets → train on first 400 → test last 100 → flag outlier entries - Financial screening: Get ratios for 50 stocks from a financial API → find anomalous ones - CRM hygiene: Pull HubSpot deals → flag deals with unusual discount/value patterns - Dependency audit: Get NPM package metrics → flag packages with anomalous quality scores - Commit review: Pull GitHub commit metadata → flag unusual commit patterns

  ConnectorNo auth

• queue_generation_result_qaA

  UwearC

  Default tool for generation-result QA. Use this whenever the user asks to QA, quality check, validate, review, inspect for defects, approve/reject, or assess already-created generation results. Do not substitute view_image for QA unless the user explicitly asks for a manual visual critique instead of the official Uwear QA pipeline. First identify the numeric generation_result_ids, then call this tool, then call read_generation_result_qa for the same IDs. QA is free. QA is built for scale — validating large batches (hundreds or thousands of results). When the user is iterating on a handful of results one by one, do not queue QA on your own initiative; run it when the user asks for it or when operating at batch scale.

  Connector

  Destructive

  No auth

• create_reviewA

  Cobalt CaptureA

  Start a new Cobalt Capture review and get a handle for filling it in. Use this to compile the findings of any site study — a usability pass, a pricing teardown, a positioning audit, a QA run — into one shareable, durable report with real screenshots. Works from any client, chat assistants included: with no browser, add_screenshot(page_url=...) renders the pages for you. Returns a `review` slug and a `claim_token` — pass BOTH back to add_screenshot / add_note to append content. Also returns a `review_url` to share and a `save_url` the human opens (while signed in) to save the review to their account permanently. The review is anonymous and auto-deletes after 30 days unless saved.

  ConnectorNo auth

• web_release_gateA

  ViewportWitness by Apex LabsA

  Choose this for a passive website release-security review of headers, cookie flags, mixed content, cross-origin script integrity, and server disclosure. It does not run browser QA, probe the site, execute code, or replace a security audit. Costs $0.05 USDC via x402. Successful paid calls settle the authorized USDC payment and create a stored report; settlement reduces the payer's balance and cannot be undone by this tool. The target website is not modified. Requires an x402-aware client to authorize payment.

  Connector

  Destructive

  No auth

• preview_ticket_exportA

  Meta CouncilB

  Preview the exact owned ticket content, destination, correlation marker and status mapping for Jira or Linear. Supply destination (Jira project key or Linear team key) for an unlinked ticket. Returns expected export hash; no provider request or external write. Requires explicit integrations:write and tickets:write. Review this preview before export; a changed ticket or provider credential needs a fresh preview.

  ConnectorNo auth

• send_template_testA

  send16-mcpB

  Send a preview of a saved workspace template to one email address, so the user can see it in a real inbox. It arrives from noreply@send16.com with a small 'Template test preview' banner and uses sample merge values (first name 'Test'). Only send to the user's own address unless they ask otherwise. Confirm the test address with the user first. Can be refused with 403 SENDING_PAUSED (workspace under review, nothing was sent, tell the user to contact support).

  Connector

  Destructive

  OAuth

• get_satellite_imageA

  TanodA

  skypeek: Get a recent satellite image of a place or coordinates. For the forecast use get_weather. Returns a recent satellite picture of a place as a base64 PNG, with the capture date, cloud cover, source and attribution: the least cloudy recent Sentinel-2 L2A scene at 10 m per pixel as true colour, NDVI (vegetation) or NDWI (water), clouds painted grey in the index views; NASA GIBS true colour (about 250 m) for areas wider than 10 km or when Sentinel-2 has no scene. Not real time (`date` is the scene day); clouds can hide the ground (404 too_cloudy, no_scene, no_imagery: not charged). Sentinel-2 data is free to use with credit; NASA GIBS has no restrictions. Not for navigation or safety. Typically 5 to 25 s (a few Sentinel-2 tiles are read and rendered). Price: USD 0.01. Free: 5 skypeek calls per IP per UTC day. Docs: https://tanod.dev/learn/satellite-image-api.html

  ConnectorNo auth