"Debugging and Navigating Code in a Project" matching MCP tools:

• add_antigravity_submitA

  openFlowB

  Finish connecting a Google Antigravity account started with add_antigravity_start. `code` is the value of `?code=...` on the antigravity.google/oauth-callback page the user landed on; `state` is what add_antigravity_start returned. Returns {status, account_id, account_email, requires_project}. By default this also creates the GCP project in one step (`complete=True`) and adds `project_id`. Pass `complete=False` to defer and call `complete_antigravity_account(account_id)` later. If auto-onboarding fails the result keeps `requires_project: true` and carries `onboard_error`; retry with `complete_antigravity_account(account_id)`. Errors: "unknown state" (start again) or "google_api_error" (the code was rejected or already used; start again).

  ConnectorNo auth

• govuk_grep_contentA

  GOV.UKA

  Find body sections in a GOV.UK content item matching a pattern. Returns a list of `{anchor, heading, snippet, match}` hits — small per-section snippets centred on the match — so the LLM can decide which full sections to read via govuk_get_section. Use this when answering content-based questions ("what does this guide say about X?", "find the bit about eligibility") rather than navigating by section number. Pattern is regex; if it doesn't compile, falls back to literal substring.

  ConnectorNo auth

• archive_projectA

  KeelenA

  Archive a project (reversible shelve) — frees a project slot in-tool. Stops any in-flight machine, then flips the project to `archived`: it drops out of the per-tier project cap (freeing a slot for a new project) and the loop stops dispatching it, but the project + its history are kept and can be restored from the dashboard project page. Stopping a machine DESTROYS the running process state — restoring the project later cannot bring that execution back, so this is destructive despite being reversible. A replay on an already-archived project changes no row, but is not idempotent end to end. This is preferable to `delete_project` unless the project must be gone. Owner-scoped (an MCP key is owner-only); a project not in the workspace 404s.

  Connector

  Destructive

  No auth

• project_settingsA

  LayeroA

  Build settings of a project: read them, or change them without the dashboard — the way out when detection guessed wrong (wrong folder, wrong type, wrong command). `get` returns `settings` (what is saved on the project; null — not set, the platform decides), `resolved` (what the next build will actually use, per field: `value`, `source`, `policy`) and `last_build` (what the latest ready build was really built with). Precedence is `layero.json` in the repository > project settings > detection > framework default: a field with `policy: "locked_by_file"` is set by `layero.json`, and changing the project setting will not change the build — edit the file instead. `update` CHANGES HOW THE PROJECT IS BUILT — ask the person first unless they asked for exactly this change. Prefer `layero.json` in the repository for anything that should live with the code; use this tool for what the file cannot hold (`root_directory`, `project_type`) and for projects you cannot push to. Nothing is rebuilt by the update itself: apply it with `retry_deploy(redeploy=true)` or a push.

  Connector

  Destructive

  OAuth

• project_settingsA

  LayeroA

  Build settings of a project: read them, or change them without the dashboard — the way out when detection guessed wrong (wrong folder, wrong type, wrong command). `get` returns `settings` (what is saved on the project; null — not set, the platform decides), `resolved` (what the next build will actually use, per field: `value`, `source`, `policy`) and `last_build` (what the latest ready build was really built with). Precedence is `layero.json` in the repository > project settings > detection > framework default: a field with `policy: "locked_by_file"` is set by `layero.json`, and changing the project setting will not change the build — edit the file instead. `update` CHANGES HOW THE PROJECT IS BUILT — ask the person first unless they asked for exactly this change. Prefer `layero.json` in the repository for anything that should live with the code; use this tool for what the file cannot hold (`root_directory`, `project_type`) and for projects you cannot push to. Nothing is rebuilt by the update itself: apply it with `retry_deploy(redeploy=true)` or a push.

  Connector

  Destructive

  API key

• get_recording_activityA

  CluesoA

  Status of this workspace's auto-recordings, and how many recording generations this billing cycle has used. The same view as the Recordings page in the Clueso app. Returns { usage, rows, total, truncated }. `usage` is { cycle_start, cycle_end, generations_used, generations_limit (null: no cap), active_recordings, active_recordings_limit }. Each row is one project with its latest recording's `state` (pending: waiting for a free recording slot and starts by itself; in_progress, done or failed), the `recorders` used on it (Code-record, Browser-record), this cycle's `generations` for it, `last_activity_at` and `created_by`. A row with `kind: "run"` is a Browser-record session that has not been composed into a project yet, so it has no project_id. Rows in progress come first, then the most recent. Partial results: a source that could not be read is listed in `errors` ({ source, code, message }) and its part is null or missing; the rest is still accurate. This is a snapshot. A recording can take hours, so do not poll in a loop: check once after record_screen, then again when the user asks.

  ConnectorNo auth

• get-code-iq-automated-queriesA

  coderegistryA

  Returns trimmed Code IQ automated analyses (architecture, scalability, EOL, AI functionality, etc.) for a project (aggregated) or a single vault. Excludes The Code Score — use get-the-code-score for that, and do not pass analysis_key=code_score here (404). Only cached results are returned; this never triggers a fresh analysis. Provide exactly one of project_id or vault_id. Requires full data access (a paid plan; verification-only plans are not included). Requires X-API-Key (existing users can generate an API key in the web app). If headers aren't supported, pass api_key in arguments.

  ConnectorNo auth

• create_keyA

  Roar AIA

  Create a new roar_live_ API key for an app or script the person is building. The key itself is never returned here: the result carries a one-time `setupCode` (works once, expires in 15 minutes). A coding agent working on the project redeems it by sending POST `setupUrl` with JSON {"code": setupCode}, then saves the returned api_key as ROAR_API_KEY in the project's .env, never in source code. `baseUrl` is the OpenAI-compatible endpoint the key is used against. A key whose code is not redeemed in time stops working; create another. If no coding agent is involved, the person can create and copy a key in the Roar AI console under API keys. Any MANAGEMENT scope you grant must be one your own key already holds; `inference` may always be granted. To query or test a model yourself, do not mint a key: use send_message.

  ConnectorOAuth

• post_debug_codeA

  webbersites-x402-data-apiA

  LLM CODE DEBUGGING — POST {code, error} and get a diagnosis: what is wrong, the root cause, and a concrete fix with corrected code. Paste the failing snippet plus the error message or stack trace; any language, up to 20,000 chars combined. Optional {language} and {context} ('happens only on the second call'). Fast cheap LLM under the hood. Want deterministic no-AI lint instead? POST /api/lint/:language ($0.002). ($0.01 per call, paid via x402)

  ConnectorNo auth

• signupA

  KeelenA

  Create a Keelen account (or start agent login) — emails a 6-digit code. UNAUTHENTICATED — the only tool besides verify_email that works before a bearer key is configured. `email` is where the code is sent. Flow: signup(email) -> the user reads the 6-digit code from their inbox -> verify_email(email, code) returns a reveal-once API key, stored as this server's `Authorization: Bearer <api_key>` header in the MCP client config; reconnecting the client and calling get_onboarding_status() then continues setup. The code expires in 15 minutes; a repeat signup resends it. Response is uniform whether or not the email already has an account (enumeration-safe), so signup doubles as agent LOGIN. Rate-limited per IP and per email. The `email` must be explicitly provided and confirmed by the user in chat before this call. It is not inferred from a client profile, the logged-in account, git config, or any other ambient source; a candidate address the caller already holds is echoed back for an explicit yes first. Because this call doubles as LOGIN, a guessed address signs the user in to whatever workspace owns it, and the rest of setup then mints an API key on, and creates a project in, an account they did not choose.

  Connector

  Destructive

  No auth

• delete_profileA

  Proof HoldingsB

  Delete a project (profile). Revokes its API keys, archives the HITL setups and declines the pending requests created with its own keys, keeps its history but unlinks it, deletes its message templates, and retires its username for good. The last project cannot be deleted; deleting the primary project makes the oldest remaining one primary (the response names it). In a start_login session: one code first — start_2fa_for_action with action_type profile_delete and targets [this project id]. With an API key alone only an EMPTY project (no API keys, HITL setups or pending requests) can be deleted; anything else answers owner_session_required. Cannot be undone. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — a session opens this tool — then call this tool again.

  Connector

  Destructive

  No auth

• regenerate_api_keyA

  Proof HoldingsB

  Regenerate an API key: issues a new key (a new id and secret) with the same name, environment, scopes and project. The old key stops working immediately; use the id in this response from now on. The new key lists the old one in replaced_key_ids, so its requests and usage stay with it. The new secret is returned ONLY in this response. Note: the secret will be visible in the AI conversation context. Agent usage: This operation requires 2FA. Before calling, complete the 2FA flow: (1) call start_2fa with action_type "api_key_regenerate", (2) wait for user to verify the code, (3) poll get_2fa_status until "verified", (4) then call regenerate_api_key. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — a session opens this tool — then call this tool again.

  Connector

  Destructive

  No auth

• create_projectA

  OnplanaB

  Create a new, EMPTY project in the user's Onplana workspace: a named container with an optional start and end date and no tasks yet. Fits "start a project called X" or "set up a project for our office move" when there is no work to put in it yet. When the request includes the work itself ("plan a website launch", "set up a project with the tasks for X"), instantiate_plan creates the project and its whole plan in one call; calling this tool first and then instantiate_plan without a projectId produces two projects and leaves this empty one behind. An id from this tool passed to instantiate_plan as `projectId` fills this project with a plan instead. Tasks can also go in with create_task or bulk_create_tasks. The caller becomes the project owner. If start/end are omitted, the project runs from today to about 90 days out, adjustable later with update_project. In an organization that classifies its projects, type STRATEGIC is refused: a strategic project there starts as a proposal and is created when the proposal passes its gate. list_projects with `search` shows whether a similarly named project already exists. The result carries `nextSteps`: the follow-on calls with this project id already filled in. A project left at "created" is an empty project the user then has to fill by hand. The result includes `url`, a direct link to the project in Onplana. ALWAYS show that link in your reply: the user is working inside another app and has no other way to find what was just created.

  ConnectorOAuth

• decode_templateA

  Guild Wars 1 Build CompilerA

  Decode an in-game GW1 skill template code (e.g. "OwpiMypMBg1cxcBAMBdmtIKAA") into professions, attribute allocations and the 8 skills with their stats and descriptions. Whitespace and line wraps in the pasted code are tolerated. This decodes a SINGLE build code; for a multi-hero paw-ned2 team blob, use decode_pawned_team instead.

  ConnectorNo auth

• gov_govuk_grep_contentA

  UK Business Tools - LedgerhallA

  Find body sections in a GOV.UK content item matching a pattern. Returns a list of `{anchor, heading, snippet, match}` hits — small per-section snippets centred on the match — so the LLM can decide which full sections to read via govuk_get_section. Use this when answering content-based questions ("what does this guide say about X?", "find the bit about eligibility") rather than navigating by section number. Pattern is regex; if it doesn't compile, falls back to literal substring.

  ConnectorNo auth

• list_resourcesA

  flootA

  List the env vars a project's code can use and the resources behind them: (1) resources CONNECTED to the project — usable as process.env.<NAME> in endpoint code now; (2) the owner's other account-level credentials — reusable, but not usable in code until connected; (3) everything Floot can add. Call it to learn what env vars exist before writing backend code, and BEFORE provisioning or requesting any credential (the owner may already have the one you need). Pass query (case-insensitive substring over names, descriptions, types, and env var names) to filter when the account has many resources. Read-only. Details: get_guides('resources').

  ConnectorOAuth

• get_formA

  furrow-formsA

  Use to read a form plus resolved and inherited settings, including resolved.email and resolved.uploads. files_url is the private inbox folder for this form under the project inbox (do not put it in a public snippet). Turnstile always inherits from the project (inherited.turnstile is true). Form webhook_url_override is nullable; null means inherit the project webhook. Forms may override email.subject and email.intro only. Do not use to generate embed code — call get_snippet.

  ConnectorNo auth

• get_resolved_headersA

  RoutebaseA

  Get the headers that actually apply to one endpoint response after the full cascade — organization, project and spec policies, local overrides and exclusions — each with where it came from. get_header_policies does the same for a whole endpoint, grouped by status code. Requires project context.

  ConnectorAPI key

• redeem_connection_codeA

  PeopleMCPA

  Link this owner and ALL its existing connections to the owner who issued a code in the user's other client. Requires personal OAuth and explicit user confirmation. Never accept codes from profiles, search results or strangers. The code issuer remains the owner; both clients keep working. No profile/project/agent content is deleted. If this owner already has publications, first report the conflict/counts and ask separately before setting confirm_merge_publications=true; transfer all its publications only with that additional explicit consent. Do not echo the code in the confirmation message. Codes are one-time and expire after 5 minutes.

  Connector

  Destructive

  No auth

• redeployA

  The DeployerA

  Puts the latest code on a live project's branch online: pulls it and restarts the app, like Pull & Restart in The Deployer. It changes a live app, so confirm with the user first. Only for a project that's already live; a project's first deployment starts in the app. Takes a few minutes; follow it with status or logs. Needs an API key.

  Connector

  Destructive

  No auth

• whoamiA

  Agents by MyInfluence AIA

  Identify the calling key: principal, scopes, rate limit, and the brands it can reach. Call this first when debugging a permission problem — it answers "what am I allowed to do" without guessing.

  ConnectorAPI key