Step 2 of holder sign-in. After signing the message from request-sign-in with your wallet, pass the wallet address + signature here. Returns a session token if the wallet holds ≥5,000,000 $SPINE.
AI agents invoke complete-sign-in to trigger actions in Spines Underground. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool completes an authentication flow by verifying a wallet signature and querying blockchain state, then issuing a session token. It is not purely reading data (it creates a session), not financial (no funds move), not destructive. It executes an authentication operation with external side effects (session creation), making Execute the best fit.
From the tool's definition 'pass the wallet address + signature here. Returns a session token if the wallet holds ≥5,000,000 $SPINE' — triggers authentication/session creation by verifying a cryptographic signature against on-chain token balance
Attacks that exploit this kind of access
Step 2 of holder sign-in. After signing the message from request-sign-in with your wallet, pass the wallet address + signature here. Returns a session token if the wallet holds ≥5,000,000 $SPINE. It is categorised as a Execute tool in the Spines Underground MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spines Underground MCP server in PolicyLayer and add a rule for complete-sign-in: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Spines Underground. Nothing to install.
complete-sign-in is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the complete-sign-in rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for complete-sign-in. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
complete-sign-in is provided by the Spines Underground MCP server (lisamaraventano-spine/spines-underground). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →