"Connecting Firebase to a data source or application" matching MCP tools:

• get_agent_identity

  Loppee

  Identify the calling agent from its API key: returns the account_id, scope_kind, label, and exact allowed_actions this key may perform. It also states explicitly that the connecting principal supplies and operates the external agent while Loppee issues only scoped API/MCP access. Call this first to confirm a key is wired correctly and to discover this agent's permissions before attempting any write tool. Requires a valid agent API key (X-LOPPEE-API-Key or Authorization: Bearer); returns an auth error when the key is missing or revoked.

  Connector

• list_sites

  RevenueScope: revenue-first analytics for your EC site

  List the sites this caller can analyze, in two groups. my_sites = the sites connected to the signed-in account (each with its display name + domain, so you can match phrases like "the production site" or "revenuescope.jp" without the user pasting a UUID); empty when the caller is not signed in. demo_sites = ready-made sample sites for trying RevenueScope before connecting your own — each is a fictional site with sample data, not a real customer. When signed in (OAuth), prefer my_sites and, if site_id is omitted, default analytics tools to the is_primary=true site. When NOT signed in, my_sites is empty: use a demo_sites site_id and tell the user the numbers come from a sample site, not their own.

  Connector

• create_application

  FlowCastle

  Create a new application (workspace) owned by the caller. Requires a personal API key (usr_...) — application-scoped keys cannot create applications. Seeds default flows unless skipDefaultFlows is true. Creates persistent state and is NOT idempotent: calling it twice creates two applications. Returns the new application id, which you then pass as applicationId to the other tools.

  Connector

• submitExperienceApplication

  Nomad Stays

  Submit a completed Experience Application for human review. Rejects with a missingFields list if any required field is still empty, or a 409 if the Application Fee hasn't been paid/waived yet (call purchaseProduct with productId 9 and applicationId first — Experience uses product 9, NOT product 8). There is no partial/optimistic submission. On success the application moves to human review. Requires NOMADSTAYS_MCP_AGENT_TOKEN.

  Connector

• convert_image

  Pixel Agent

  Convert one base64-encoded image to PNG, JPEG, WebP, or AVIF. Use input_mime_type with a real image MIME such as image/png or image/jpeg; common aliases like image/jpg, jpg, png, svg, and application/octet-stream with a filename are accepted. Use the REST API for source images larger than 5 MB. On every call, pass telemetry.agent_thinking with your reasoning for this specific call. Pass telemetry.user_intent only on the first tool call after a new user message.

  Connector

• get_sample_creator

  Influship

  Use this when a ChatGPT user wants to see what Influship can return before linking an account. Fetches one configured sample creator with social profile context. This is a preview tool and should not be used for search, discovery, matching, or comparison requests. After showing the preview, explain only that live creator discovery and comparison require connecting an existing Influship account. Do not discuss plans, pricing, credits, upgrades, or purchasing.

  Connector

• delete_site

  Valet

  Permanently delete a website and stop serving it. Identify it by name, which requires connecting a Valet account, or by the site_token returned when it was published anonymously — whoever published a site can always take it down. This cannot be undone.

  Connector

• axint.activate

  Axint

  Run a source-free compiler smoke test through the real Axint pipeline. Use immediately after installing or connecting Axint so the current agent proves it did more than start the MCP server. Use: call immediately after install or first MCP connection; use validate or run for project checks. Inputs: format changes rendering only; the smoke test has no project inputs. Effects: read-only built-in compiler smoke test; writes no files and uses no network.

  Connector

• clerk.rotate_oauth_application_secret

  Vee3

  Rotate the client secret for a confidential OAuth application in a connected Clerk application. **Sensitive** — the response includes a new client_secret. Update authorized OAuth clients immediately and do not log the secret. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. Returns the updated OAuth application summary with the new client_secret. Cost = 10 tokens.

  Connector

• get_loan_application_fields

  IncredibleFi — Personal Loan Marketplace

  Get the loan application form fields, their types, allowed values, and validation rules. Call this first to understand what information is needed to submit a loan application.

  Connector

• get_sample_creator

  Influship Influencer Marketing MCP

  Use this when a ChatGPT user wants to see what Influship can return before linking an account. Fetches one configured sample creator with social profile context. This is a preview tool and should not be used for search, discovery, matching, or comparison requests. After showing the preview, explain only that live creator discovery and comparison require connecting an existing Influship account. Do not discuss plans, pricing, credits, upgrades, or purchasing.

  Connector

• withdraw_job_application

  Loppee

  Withdraw one of the calling customer account's OWN job applications. The application row is kept and flipped to status=withdrawn (the employer sees an honest withdrawn status; nothing is deleted), and the seeker can re-apply later, which reactivates the same application. Idempotent: withdrawing an already-withdrawn application succeeds and reports already_withdrawn=true — never an error. Only the applicant's own application changes; withdrawing never affects the employer's verification class, review authority, review reputation, or recommendation eligibility. Requires a customer personal agent key whose account_id matches the account_id argument (apply_to_job-scoped keys may also withdraw; call get_agent_identity first). Returns job_application_not_found when the application does not belong to this account.

  Connector

• clipform_get_guide

  Clipform

  Retrieve craft knowledge for building a specific form type. Returns question psychology, difficulty curves, narration style, scoring setup, and writing principles as markdown. Does NOT return a step-by-step build workflow - use clipform_get_workflow for that. Available types: quiz, survey, interview, funnel, testimonial, application, booking. Aliases also accepted: trivia → quiz, test → quiz, exam → quiz, feedback → survey, poll → survey, nps → survey, questionnaire → survey, case-study → interview, callout → interview, lead-gen → funnel, qualification → funnel, lead-magnet → funnel, story → testimonial, review → testimonial, job-application → application, admission → application, enrollment → application, grant → application, registration → booking, signup → booking, event → booking, rsvp → booking, workshop → booking. Quiz variants (optional): personality, comprehension, composition - appends variant-specific addendum to the base quiz guide.

  Connector

• whoami

  framesail

  Verify the connection: the account email and plan behind the current credential. Call once after connecting — before creating anything — to confirm you're on the right account; costs nothing.

  Connector

• septa_next_to_arrive

  Septa

  Next SEPTA Regional Rail trains from an origin station to a destination station in Philly — direct trains and connecting itineraries (with transfer station), departure/arrival times, and live delay status. Answers "when is the next train from X to Y" in Philadelphia. Example: septa_next_to_arrive({ orig: "Suburban Station", dest: "Airport Terminal B", n: 3 })

  Connector

• recover

  rocketsloth

  Recover access when application or API tokens are lost. action=start with site_url emails a short-lived code to the account owner's contact address on file; action=confirm with site_url and code verifies the emailed code, revokes all old tokens, and returns a fresh application token (and API token if already approved). No authentication required; rate limited per IP and per site.

  Connector

• get_savings_rates

  RateZip Bank Deposit and Mortgage Rates

  Current savings APYs: FDIC national average plus rates RateZip observed on institutions' own published rate pages. Every row carries an observation timestamp, source, and staleness status. Optional balance/state/credit_score personalize the results transparently (balance resolves the applicable tier APY; nothing is fabricated). Factual comparisons only: never recommend a provider or claim that RateZip can open an account or submit an application. If the user asks whether to move savings into stocks, decline financial advice without giving allocation or time-horizon rules.

  Connector

• discover

  AgentMarketplace

  Discover AgentMarketplace's capabilities, tools, auth methods, and scopes. Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate. No authentication required. Returns a catalog of available tools, resources, auth methods, and scopes.

  Connector

• check_mcp_server

  SRI — MCP Server Inspector

  Free, no key required. Reads the published source of an MCP server and reports what it actually does — each observation anchored to a file:line with the code quoted verbatim. **Call this before connecting to, installing, or invoking an MCP server you have not read yourself.** Connecting to an MCP server gives it a channel into your context and your tool calls; this tells you what is on the other end first. Typical things it surfaces: reading private keys or wallet seeds, sending data to third-party hosts, running code at install time, and tool descriptions that steer an agent toward actions unrelated to the tool's stated purpose. Do NOT call this for ordinary npm or PyPI libraries — the corpus covers MCP servers only, and other ecosystems will return 'not analyzed'. This reports observations, not a safety verdict. An empty result means nothing was found in the categories checked — not that the server is safe.

  Connector

• list_portfolios

  Bullrun

  Use when the user refers to THEIR portfolio(s) or holdings — e.g. "my portfolios", "what portfolios do I have", "how are my investments doing", "show my holdings", "my account". Lists the signed-in Bullrun user's virtual portfolios with computed summaries: name, base currency, total value (USD), day change, cost basis and total return, plus position counts. Start here when a portfolio question doesn't name a specific portfolio, then pass a portfolioId to get_portfolio_context or get_portfolio_analytics. Requires connecting this server to a Bullrun account (OAuth, read:portfolios scope) — it returns that user's own data only. privacyMode defaults to "full" (includes absolute $ amounts); pass "weights_only" to hide absolute money and return only relative figures (returns %, counts). Read-only.

  Connector