Is the Solvscore MCP server down?

mcp-registry/com.solvscore/mcp · v3.2.4

Also listed as github/shawnhvac/solvscore-mcp, glama/shawnhvac/solvscore-mcp

As of 2026-10-27 07:00 UTC, the Solvscore MCP server is up with a Glimind reliability score of 86/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 13 outages in 90 days, with a median recovery of 8 minutes.

Credit scores for AI agents. Underwrite an unknown counterparty before extending credit.

Point your MCP client at this streamable-http endpoint: https://solvscore.com/mcp

Agent-readiness: C (75/100)

What to fix (3)

Auto-fix: 13 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 15 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fcom.solvscore%2Fmcp/fixes

{
  "name": "get_agent_attestations",
  "description": "[FREE] Read the onchain attestations naming an AI agent's wallet on Base, and what they\nare worth in SolvScore's underwriting. Accepts a Base wallet address, an agent name, or\na SolvScore credit file id.\n\nReturns points_awarded, whether the wallet carries an unrevoked KYC-backed Coinbase\nVerified Account, how many attestations were ignored because their attester is not\nallowlisted, and the schema uids a company can attest into to report work an agent\nactually delivered.\n\nCheck this before extend",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent_or_wallet"
    ],
    "properties": {
      "agent_or_wallet": {
        "type": "string"
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}

{
  "name": "get_agent_credit_score",
  "description": "[FREE] Look up an AI agent's SolvScore credit file before you transact with it.\nAccepts an agent name, id, or Base L2 wallet address.\nReturns trust_score (0-100), badges (reputation bonds held), a nested credit object\ncarrying credit_limit and apr_bps, plus two counterparty red flags worth checking\nbefore you extend anything: sybil_flagged and cooling.\nFree and unauthenticated - no API key, no payment header.",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent"
    ],
    "properties": {
      "agent": {
        "type": "string"
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}

{
  "name": "get_credit_improvement_path",
  "description": "Counterfactual credit explanation: the minimal quantified actions an agent\ncan take to improve its SolvScore status. Free. For each target (next badge,\nthe 85-point underwriting floor, or an explicit trust-score target) returns\nper-action unit counts, points per unit, headroom to each scoring cap, and\nwhether that single path reaches the target. Also explains the hard-collateral\npath (which lifts the limit and cuts the APR without moving the score).",
  "inputSchema": {
    "type": "object",
    "required": [
      "agent"
    ],
    "properties": {
      "agent": {
        "type": "string"
      },
      "target": {
        "type": "number",
        "default": 0
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/com.solvscore/mcp"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/com.solvscore/mcp"}) over MCP.

Passed

• Every tool has a well-formed, typed input schema.
• No tool-poisoning patterns (hidden characters, instruction overrides, concealment, secret access, tool shadowing).
• Compact tool list (~2,958 tokens).
• Tool names are unique and portable across clients.
• Speaks MCP 2025-06-18.
• 99.74% uptime over 30 days.
• No breaking contract changes in 30 days.

Largest tool definitions

• register_agent ~224 tokens
• underwrite_agent_loan ~213 tokens
• get_solvscore_agent_dashboard ~197 tokens
• get_agent_attestations ~195 tokens
• get_liquidity_stress_test ~191 tokens

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.solvscore%2Fmcp.svg)](https://glimind.com/server/mcp-registry%2Fcom.solvscore%2Fmcp?ref=badge)

<a href="https://glimind.com/server/mcp-registry%2Fcom.solvscore%2Fmcp?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.solvscore%2Fmcp.svg" alt="MCP agent-readiness"></a>

.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fcom.solvscore%2Fmcp.svg
   :target: https://glimind.com/server/mcp-registry%2Fcom.solvscore%2Fmcp?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:a8452426002752f7…, first seen 2026-10-17, included at leaf 9812 of 77,973. Version history · verify what your client received.

Tools (20)

• get_agent_attestations
• get_agent_credit_score
• get_credit_improvement_path
• get_credit_leaderboard
• get_credit_market_stats
• get_kya_credential
• get_liquidity_stress_test
• get_scoring_weights
• get_solv_quote
• get_solvscore_agent_dashboard
• get_solvscore_receipts
• register_agent
• solv_buy_kit
• solv_program_info
• solv_rebate_round_detail
• solv_rebate_rounds
• solv_register_wallet
• solv_snapshot_and_distribution
• underwrite_agent_loan
• verify_solvscore_receipt

Compare: most reliable finance servers · most reliable retrieval servers · most reliable knowledge servers

claude mcp add --transport http glimind https://glimind.com/mcp

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

FAQ

Is the Solvscore MCP server down right now?

As of 2026-10-27 07:00 UTC, the Solvscore MCP server is up with a Glimind reliability score of 86/100 (grade B). Over the last 30 days it answered 99.7% of Glimind's liveness checks. It had 13 outages in 90 days, with a median recovery of 8 minutes.

How many tools does Solvscore MCP server provide?

Solvscore MCP server advertises 20 tools, including get_agent_attestations, get_agent_credit_score, get_credit_improvement_path, get_credit_leaderboard, get_credit_market_stats.

How do I install Solvscore MCP server?

Point your MCP client at this streamable-http endpoint: https://solvscore.com/mcp

Is the Solvscore MCP server safe to connect to an AI agent?

Glimind scanned all 20 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Solvscore MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.