Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
CorroborateMe is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Prove end users to agents and apps: login-links, OIDC clients, and API keys over remote MCP
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http corroborateme-mcp https://corroborateme.com/mcp
# 2 — ask your agent for something these tools do
# agent_bootstrap, budget_get, billing_checkout and 10 more
CorroborateMe costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Its publisher asks you to sign in with OAuth: run /mcp in Claude Code and pick this server, and it opens a browser for that once.
claude mcp add --scope user --transport http corroborateme-mcp https://corroborateme.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
13 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Show how to start zero-human company onboarding. This call does not create a company, send email, or mint a bootstrap token or an aa_ key. MCP requires a company API key (aa_...) or an MCP OAuth access token before any tool runs. Returns message, path (/api/agents/bootstrap), body (company_name…
No parameter schema on file.
Read remaining quotas and plan entitlement for the authenticated company. Call this when you need to know whether an active plan is in effect before registering OIDC clients or creating login links. Minting an API key does not require an active plan. Requires a company API key (aa_...) or an MCP…
No parameter schema on file.
Create a Stripe Checkout session for the authenticated company so a human can subscribe to Pro. Requires a company API key (aa_...) or an MCP OAuth access token. It does not accept a console session or a bootstrap token, and it does not mint a company or an aa_ secret. Returns url. Creating the…
No parameter schema on file.
Return prepaid Pro purchase instructions. This tool does not charge a card, grant Pro, or return an aa_ secret. MCP requires a company API key (aa_...) or an MCP OAuth access token; a bootstrap token is not accepted on this call. Optional sku defaults to pro_prepaid_30d. On success, returns sku,…
No parameter schema on file.
Create a billing portal URL for the authenticated company. Use this when a human needs to update a payment method, view invoices, or change an existing subscription. Requires a company API key (aa_...) or an MCP OAuth access token. Returns url when Stripe is configured and the company has a Stripe…
No parameter schema on file.
Mint an additional company API key. The full secret is returned once (only a hash is stored) and cannot be fetched again. An active plan is not required. Requires a company API key (aa_...) or an MCP OAuth access token. Returns id, secret, and prefix. Creating a key can be rate limited. Optional…
No parameter schema on file.
Register an OIDC relying-party client that uses CorroborateMe as the identity provider, with RP-initiated logout enabled. Use this for your app's own OIDC login. MCP hosts connect through protected-resource metadata and dynamic client registration, not this tool. Requires a company API key…
No parameter schema on file.
Store or replace an encrypted integration secret for a provider such as Google or Apple. Use this before login-link social sign-in needs that provider's credentials. Requires a company API key (aa_...) or an MCP OAuth access token and an active plan. Returns id and prefix (first four and last four…
No parameter schema on file.
List this company's stored integrations. Use this to see which providers are configured before calling integration_upsert. Requires a company API key (aa_...) or an MCP OAuth access token. Returns a JSON array of id, provider, label, secret_prefix, meta, created_at, and rotated_at. Full secrets…
No parameter schema on file.
Mint a one-time human login URL and session id so you can prove an end user. Call webhook_allowlist_add first when using webhook, redirect, or form_post. Requires a company API key (aa_...) or an MCP OAuth access token and an active plan. A missing subscription returns an error result with code…
No parameter schema on file.
Poll one login-link session until the human finishes, and read any notify errors. Use this after create_login_link, passing that call's sessionId as session_id. Requires a company API key (aa_...) or an MCP OAuth access token. Returns id, status, state, user_id, email, claims, expires_at,…
No parameter schema on file.
Send the signed login webhook again for a session that already used the webhook method. A prior delivery failure is not required. The session must be completed or consumed. Delivery already tries up to 3 times (immediately, then after 500ms, then after 2000ms) on HTTP 408, 429, 5xx, and network…
No parameter schema on file.
Allow a callback URL prefix for later login-link notify. Call this before create_login_link when methods include webhook, redirect, or form_post. Requires a company API key (aa_...) or an MCP OAuth access token. Pass url_prefix, at least 4 characters, for example https://hooks.example.com/ or…
No parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install CorroborateMe or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither: the repository linked on this page is where this record was collected from, not a copy of what the address serves, so it is not graded in its place. So there is no grade — not a withheld one, an unmeasured one.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.1.3.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish CorroborateMe can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.