Skip to main content
Glama
821,828 tools. Updated 2026-11-22 17:50

"Graphical user interface (GUI)" matching MCP tools:

  • Provision a peer and return its WireGuard configuration. Three routing modes, and the right one depends on the machine. source (the default) sends only traffic from the leased address through us and leaves the default route alone — but it is written with wg-quick PostUp rules that invoke `ip`, so it runs on Linux under wg-quick and nowhere else. On macOS it aborts and deletes the interface. full works in every client but claims the default route, so it cannot run beside an always-on corporate VPN. destinations routes only the addresses you name. It needs no PostUp and takes no default route, so it runs in any client on any platform, and it matches what is usually being bought — one partner seeing a fixed address. It survives beside a VPN that installs a default route, but not one that captures traffic below the routing table. It cannot receive inbound connections from anywhere but those destinations.
    ConnectorNo auth
  • List the contrib classes that extend, implement or use a core class, interface or trait, one row per edge with file and line, paged. Example: "who subclasses FormBase". Call-site counts: list_symbol_users. The symbol's status: lookup_core_symbol. - target: with or without the leading backslash. An unknown target is refused with a pointer at lookup_core_symbol; a fragment there lists candidates. rel_kind: one of extends, implements, uses_trait. project: one machine name. - Development branches only. edge_count: every edge. project_count: projects. count: edges after the per_project cap. project_edges on each row: the project's full count. per_project=50 with project= lists one project in full. - Rows are ordered by project installs, project, source_fqn. Each row: project, branch, installs, source_fqn, rel_kind, file, line, project_edges. limit ≤ 100. next_offset is absent on the last page.
    ConnectorNo auth
  • Look up the nodes, zones, stations or fuels in a stream, with how far back each goes. Use it before query_stream: names are verbatim and never to be guessed. `facets` counts the entities by type. Args: slug: The stream. search: Case-insensitive substring of the entity name ("HOUSTON", "HB_", "KAUS"). entity_type: Only one type — HUB, LOAD_ZONE, RESOURCE_NODE, INTERFACE… limit: At most this many (1–2000).
    ConnectorOAuth
  • Shows the user a picture of the board right in the conversation, as the editor draws it, with a button that opens it in Perfboard Designer. Only in clients that show MCP Apps (e.g. Claude, ChatGPT); elsewhere the user sees nothing, so give them make_share_link's link too. The picture goes to the user, not to you: to look at the board yourself, use render_board.
    ConnectorNo auth
  • Orders the renewal of one of the user's LEIs. This commits the user to paying, so only call it after showing the user the price from get_renewal_quote and getting their explicit agreement. paymentMethod 'card' returns paymentUrl, Global FinReg's renewal page for the LEI: give it to the user, who signs in to their Global FinReg account and pays by card there (never ask for card details); the renewal is processed once paid. paymentMethod 'invoice' confirms the renewal straight away and returns the invoice PDF for the user to pay by bank transfer.
    ConnectorOAuth
  • Find where a feature lives in the Buzzberg interface. Read-only, no data is changed. Use this for every "where do I find X", "how do I open X", "which section has X" question instead of guessing. It searches only the verified navigation catalog of user-facing surfaces; internal, admin and API routes are deliberately not covered. If nothing matches, say the location is not confirmed rather than inventing one. Args: query: What the user is looking for, in their own words (any language). locale: UI locale for section names, e.g. "en", "ru", "ko". limit: Max matches to return (default 5).
    ConnectorOAuth

Matching MCP Servers

Matching MCP Connectors

  • Stop somebody reaching the user: refuses a waiting request, ends an accepted contact, or blocks an address pre-emptively — one act for all three. Nothing is sent and the other person is not told. A block is symmetric, so the user cannot write to them either while it stands; unblock_contact lifts it. Call it only when the user asks for it in their own message.
    Connector
    Destructive
    API key
  • Create or update a service's horizontal autoscaling settings in one call — enable/disable, min/max replicas, target CPU %, target memory %, and the scale-up/scale-down stabilization windows. Same operation as saving the web console's Autoscaling dialog. ONLY call this after the MANDATORY CONFIRMATION GATE: the full final settings were shown to the user and they explicitly confirmed. Pass ALL fields every time (merge the user's changes into the current settings from komuta_get_service_hpa) — this is a full replace, not a patch. Resolve the id from the NAME the user gave — never ask the user for an id. Returns: { serviceName, settings: { mode: 'Disabled' | 'Pinned' | 'Autoscaling', isActive, minReplicas, maxReplicas, targetCPUUtilizationPercentage, targetMemoryUtilizationPercentage, scaleUpStabilizationWindowSeconds, scaleDownStabilizationWindowSeconds } } — the settings as saved by the backend. Show user: confirmation that autoscaling was saved, plus every returned settings field in plain language. Never show user: serviceId and any other internal ids from the underlying payloads. Sends: the complete settings object the user confirmed at the confirmation gate — user-changed fields from their chat message, everything else carried over unchanged from komuta_get_service_hpa; whether it creates or updates is resolved internally from the service's current state.
    Connector
    Destructive
    OAuth
  • Submit a content correction, copyright concern, or factual error report. USE WHEN: user (via your interface) flags a wrong answer, broken translation, attribution issue, or DMCA concern. INPUTS: at least one of (questionId UUID, questionText, questionUrl), type (translation|factual|inappropriate|attribution|other), comment (optional, max 2000), reporterEmail (optional). OUTPUT on success: {ok:true, reportId}. On failure the result is marked isError:true with structuredContent {error, message} — error codes: invalid_input, not_found, rate_limit_exceeded (per-IP 5/min), internal_error.
    ConnectorNo auth
  • Rewrite a prompt to score higher on the PQS rubric, AND show before/after output comparisons so the user can see the impact. Returns the optimized prompt, the original PQS score, the optimized PQS score, and side-by-side sample outputs from a frontier model using both versions. USE WHEN: - The user got a low score from score_prompt and asks how to improve. - The user explicitly asks to "improve" / "rewrite" / "fix" / "optimize" a prompt they pasted. - The user is dissatisfied with output quality from a previous prompt and asks how to get better results. - score_prompt returned a suggestion to invoke this tool. DO NOT USE WHEN: - The user just asked for a score (use score_prompt only — don't double up). - The user wants you to write a new prompt from scratch (write it directly). REQUIRES: A PQS API key from a Pro subscription ($19.99/month, 1,000 calls/mo, includes batch + A/B comparison). If the user has not provided one, the tool returns a clear subscription URL — pass that response to the user verbatim. Do not invent or guess API keys. There is no free trial of this tool; the user must subscribe before the first call. COST: Counted against your Pro subscription's monthly call quota. LATENCY: ~6-8 seconds.
    ConnectorNo auth
  • Rewrite a prompt to score higher on the PQS rubric, AND show before/after output comparisons so the user can see the impact. Returns the optimized prompt, the original PQS score, the optimized PQS score, and side-by-side sample outputs from a frontier model using both versions. USE WHEN: - The user got a low score from score_prompt and asks how to improve. - The user explicitly asks to "improve" / "rewrite" / "fix" / "optimize" a prompt they pasted. - The user is dissatisfied with output quality from a previous prompt and asks how to get better results. - score_prompt returned a suggestion to invoke this tool. DO NOT USE WHEN: - The user just asked for a score (use score_prompt only — don't double up). - The user wants you to write a new prompt from scratch (write it directly). REQUIRES: A PQS API key from a Pro subscription ($19.99/month, 1,000 calls/mo, includes batch + A/B comparison). If the user has not provided one, the tool returns a clear subscription URL — pass that response to the user verbatim. Do not invent or guess API keys. There is no free trial of this tool; the user must subscribe before the first call. COST: Counted against your Pro subscription's monthly call quota. LATENCY: ~6-8 seconds.
    ConnectorNo auth
  • Public onboarding hint for an agent whose user isn't linked to Vaaya yet. Returns where the human should go to connect (and sign up if new). Call this when vaaya_test_connection reports needs_auth, or any tool returns unauthorized, then relay the instructions to the user. If the user IS already linked it returns `first_call` instead — show `first_call.show_to_user` as written so they know what to try.
    ConnectorNo auth
  • Create a database user for a Cloud SQL instance. * This tool returns a long-running operation. Use the `get_operation` tool to poll its status until the operation completes. * When you use the `create_user` tool, specify the type of user: `CLOUD_IAM_USER`, `CLOUD_IAM_SERVICE_ACCOUNT`, or `BUILT_IN`. * By default the newly created user is assigned the `cloudsqlsuperuser` role, unless you specify other database roles explicitly in the request. * You can use a newly created user with the `execute_sql` tool if the user is a currently logged in IAM user. The `execute_sql` tool executes the SQL statements using the privileges of the database user logged in using IAM database authentication. The `create_user` tool has the following limitations: * To create a built-in user with password, use the `password_secret_version` field to provide password using the Google Cloud Secret Manager. The value of `password_secret_version` should be the resource name of the secret version, like `projects/12345/locations/us-central1/secrets/my-password-secret/versions/1` or `projects/12345/locations/us-central1/secrets/my-password-secret/versions/latest`. The caller needs to have `secretmanager.secretVersions.access` permission on the secret version. * The `create_user` tool doesn't support creating a user for SQL Server. To create an IAM user in PostgreSQL: * The database username must be the IAM user's email address and all lowercase. For example, to create user for PostgreSQL IAM user `example-user@example.com`, you can use the following request: ``` { "name": "example-user@example.com", "type": "CLOUD_IAM_USER", "instance":"test-instance", "project": "test-project" } ``` The created database username for the IAM user is `example-user@example.com`. To create an IAM service account in PostgreSQL: * The database username must be created without the `.gserviceaccount.com` suffix even though the full email address for the account is`service-account-name@project-id.iam.gserviceaccount.com`. For example, to create an IAM service account for PostgreSQL you can use the following request format: ``` { "name": "test@test-project.iam", "type": "CLOUD_IAM_SERVICE_ACCOUNT", "instance": "test-instance", "project": "test-project" } ``` The created database username for the IAM service account is `test@test-project.iam`. To create an IAM user or IAM service account in MySQL: * When Cloud SQL for MySQL stores a username, it truncates the @ and the domain name from the user or service account's email address. For example, `example-user@example.com` becomes `example-user`. * For this reason, you can't add two IAM users or service accounts with the same username but different domain names to the same Cloud SQL instance. * For example, to create user for the MySQL IAM user `example-user@example.com`, use the following request: ``` { "name": "example-user@example.com", "type": "CLOUD_IAM_USER", "instance": "test-instance", "project": "test-project" } ``` The created database username for the IAM user is `example-user`. * For example, to create the MySQL IAM service account `service-account-name@project-id.iam.gserviceaccount.com`, use the following request: ``` { "name": "service-account-name@project-id.iam.gserviceaccount.com", "type": "CLOUD_IAM_SERVICE_ACCOUNT", "instance": "test-instance", "project": "test-project" } ``` The created database username for the IAM service account is `service-account-name`.
    ConnectorNo auth
  • USE ONLY when the user explicitly asks to check whether their LLM brand Discoverability Assessment is ready. Part of the flow started by `start_discoverability_assessment`. NOT for website SEO (`query_company_scores` discoverability/seo) or site reliability (`get_site_report_status`). Checks the status of a Discoverability Assessment job queued by `start_discoverability_assessment`. Call this tool ONLY when the user explicitly asks to check status — never poll automatically or in a loop. REQUIRED INPUT: the `JobId` returned by `start_discoverability_assessment`. If the user did not provide it and it is not in conversation context, ask them or re-run `start_discoverability_assessment`. STATUS VALUES (from the API): - 201 — job is queued; tell the user it is still waiting and they can ask again later. - 202 — job is in progress; tell the user it is still running and they can ask again later. - 200 — job finished; `ReportId` is populated and `IsFinished = true`. Call `get_discoverability_assessment` with the `ReportId` to retrieve the full analysis and human-friendly summary. - 400 — bad request (invalid jobId, etc.); do not retry blindly — verify the jobId. - 500 — job errored out; surface the API message to the user. DO NOT POLL: After calling this tool, if status is 201 or 202, report the current state to the user and stop. Do NOT call this tool again unless the user explicitly asks to check status. Do not call `get_discoverability_assessment` until `IsFinished = true` and a `ReportId` is available.
    ConnectorNo auth
  • Generate per-user short URL variants for an existing parent short URL. Each user receives their own unique short link that resolves to the same destination as the parent, but identifies the user on click — used for fan-level click attribution in email/SMS campaigns. The parent short URL must already exist (create it first with nevent_create_short_url). Requires: parentShortCode (from nevent_list_short_urls) and userIds (list of user IDs). Returns: parentShortCode, totalRequested, totalCreated, createdLinks (array of ShortUrlDTO with userId, shortCode, shortUrl per user). Use nevent_get_short_url_campaign_metrics afterwards to track aggregate CTR. WRITE operation — requires STANDARD or FULL operation mode. In READ_ONLY mode this tool returns an operation_not_permitted error immediately without making any API call. Note: parentShortCode is sent in both the URL path and request body — they must match (validated server-side).
    ConnectorNo auth
  • Answer one booking request sent to the signed-in user. Get the id from my_bookings first. Always read the request back to the user and get a clear yes before calling this: it is their answer to a real person, not yours. Accepting does not arrange a time — the user still has to call them — so say that.
    ConnectorNo auth
  • Cancel an order that has not shipped. This cannot be undone. Call it first with confirm=false to get the order details, show them to the user, and only after the user explicitly agrees call again with confirm=true.
    Connector
    Destructive
    No auth
  • Update an interface contract. Content merges by key: send only changed content keys, using arrays for metadata, to preserve existing scalar/list values. PUT requires endpoints, interface_type and description_payload; an omitted lock stays unchanged. Prefer interface_contracts_patch for partial edits. A locked interface contract refuses changes to its interface type, payload and wording, and deletion, until a person unlocks it in Entalpa; its endpoints and implementation progress (implementation_status, implementation_notes, code_reference, test_reference, tests) can still be written, and labels_assign still labels it. lock: true locks the row; lock: false is ignored, since only a person unlocks, in Entalpa.
    ConnectorOAuth
  • Create a collection for the user's Mobbin MCP connection, and return its id and link. It starts empty: call save_content with the returned id to add screens, flows or sections. It is private: only the user and their teammates can open the link, and say so when you give it out. The user can make it public on mobbin.com. Use it when the user asks for a new collection, or wants to save into one that list_collections does not have. Collection names are not unique, so check list_collections first when the user may already have one with that name.
    ConnectorOAuth
  • Turn Telegram notifications for a feed on (on: true) or off (on: false). On: the bot sends the user every new matching job, filtered by the feed's ai_filter; needs a free slot (up to 5 feeds with alerts) or fails with feed_limit_reached. Off: the feed stays for you only (up to 5 such feeds). Ask the user first, then pass user_confirmed: true. The user is notified in Telegram.
    ConnectorOAuth
  • Sign the user up for an email reminder before EVERY upcoming match of a football team. Matches added or moved later are covered too, so the user never has to come back. Use it when the user says every match, all matches, whenever <team> plays, or follow <team>; for one match, use remind_me. Ask the user for their email address first (never guess it). A new address gets one confirmation email, and the reminders start once the user clicks the link in it. Every reminder has a link to stop following. Only for teams, never for personal appointments. When beep.me is connected with sign-in, leave email out: it is on at once, with no confirmation email.
    ConnectorNo auth