SecondAppraisal helps AI agents assist vehicle owners with total-loss insurance claims by estimating fair market value, comparing similar vehicle listings against insurer offers, uploading valuation reports, checking state-specific appraisal rules, and submitting appraisal consultation requests.
Hermes is Nous Research's command-line agent. MCP servers are declared in its YAML config and reloaded without a restart.
This guide connects SecondAppraisal MCP to Hermes through MewCP, so Hermes can use SecondAppraisal MCP's 5 tools, like submit_total_loss_intake, get_intake_status and upload_valuation_report.
SecondAppraisal MCP needs no credentials, but every call still runs through MewCP: scoped, checked and logged like any other.
More apps
Clerk enables AI agents to manage application authentication, user accounts, organizations, sessions, and access permissions, including inspecting user profiles and configuring authentication workflows.
OnChainDiligence helps AI agents evaluate autonomous payment proposals against caller-defined policies, retrieve signed payment receipts, and independently verify receipt integrity and authenticity. Provides evidence for auditing agent payment decisions without holding funds, signing transactions, or executing payments.
ConsentStack automates website cookie consent management by creating and publishing consent banners, configuring privacy settings, detecting and categorizing tracking scripts, running compliance scans, and reviewing consent analytics and logs for GDPR and other privacy regulations.
CourtListener provides searchable access to U.S. case law, court opinions, dockets, judicial decisions, and legal filings. Find cases by citation, keyword, court, or judge; retrieve opinion texts and docket records; and research legal precedents using data from federal and state courts.
Other clients
SecondAppraisal MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact SecondAppraisal MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit config.yaml in your Hermes config directory (~/.hermes).
Put this under the top-level "mcp_servers:" key.
Run /reload-mcp in Hermes, or start a fresh session. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Submit a vehicle owner's total-loss situation to SecondAppraisal on their behalf. Minimum: one of customer.phone / customer.email, your `agent` self-identification, and a `consent.attestation`. Returns a receipt with `customer_confirmation_url` (one tap confirms), a relayable `customer_message`, an optional `preliminary` market read, `contact_policy` (we will email/text a welcome and a person will call to confirm the request came from the customer or their agent), and `pricing` — the consultation is free; if the owner wants more, Appraisal Research is $199 (paid up front, no guarantee) or Appraisal Research + Negotiation is $495 with a $25 discount for customers you send ($470; a card HOLD captured only after the settlement improves by $1,000+, otherwise nothing is charged). The $25 applies to representation only. You may quote `pricing` verbatim; payment always happens on our site by the customer's own click (`checkout` links appear once they have confirmed) — never collect card details. Read `customer_message` to the user verbatim.
Fetch the current receipt for a submitted intake (status, confirm link while still confirmable, preliminary).
Attach the insurer's Market Valuation Report (CCC / Mitchell PDF) to a submitted intake. We parse it (vehicle, mileage, offer, insurer, loss date) and refresh the preliminary. Allow up to two minutes.
A no-commitment early market read for a vehicle: comparable listing prices near the customer (10th percentile / median / 90th), an odometer-adjusted mid, and the gap vs the insurer's offer. Not an appraisal. Nothing is stored about the customer.
State-specific total-loss facts: threshold and method, whether an independent appraiser must be licensed there, whether third-party appraisals are allowed, statute citations, must-know rights, common pitfalls, and the consumer hotline.
