AI & Machine Learning

solvscore.com

Provides credit scoring and loan underwriting services for AI agents.

1 endpoint7 known toolsFirst detected August 26, 2026Last detected August 26, 2026

ENDPOINT 1

https://solvscore.com/mcp

No auth detected

MCP server metadata

Name: SolvScore
Version: 3.2.4

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

SolvScore is a credit bureau for autonomous AI agents on Base L2. It underwrites agents that own nothing, pricing credit from verified work history instead of assets, and raises the limit when tokenized collateral is posted. Call get_agent_credit_score(agent) before you extend credit, prepay, rent compute to, or delegate paid work to an unknown agent. Call underwrite_agent_loan(agent, principal) for a real approve/decline with a credit limit and an APR. This bureau declines: roughly half of all requests are refused, so a decline is a real signal about the counterparty rather than a formality. Reputation sets the floor and tokenized stocks raise the ceiling — passing tier1_value moves an agent from the reputation tier to the hard-collateral tier, which lifts the limit and cuts the rate. Every tool is free and unauthenticated. Decisions are advisory: settle them in your own contract or through the SolvScore credit manager on Base L2.

Known tools 7

get_agent_credit_score

[FREE] Look up an AI agent's SolvScore credit file before you transact with it.

Inferred read-only

underwrite_agent_loan

[FREE] Get a real underwriting decision on a loan to an AI agent.

Inferred read-only

register_agent

[FREE] Open a SolvScore credit file for your own agent so it can be underwritten.

Inferred read-only

get_credit_market_stats

[FREE] Protocol-wide SolvScore stats: agents scored, total credit capacity in USDC, reputation bonds outstanding and slashed, quotes issued versus approved (the decline rate), plus average and top trust score.

Inferred read-only

get_credit_leaderboard

[FREE] List the most creditworthy agents by SolvScore, with bond counts and slash history.

Inferred read-only

get_agent_attestations

[FREE] Read the onchain attestations naming an AI agent's wallet on Base, and what they are worth in SolvScore's underwriting.

Inferred read-only

get_scoring_weights

[FREE] Read the governance-parameterized weights behind every SolvScore, so you can audit exactly how a score was produced and what behaviour raises or lowers it.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.solvscore]
url = "https://solvscore.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "solvscore": {
      "type": "http",
      "url": "https://solvscore.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: solvscore
Remote MCP URL: https://solvscore.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "solvscore": {
      "url": "https://solvscore.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "solvscore": {
      "type": "http",
      "url": "https://solvscore.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "solvscore",
  "transport": "streamable-http",
  "url": "https://solvscore.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.