# SolvScore > Credit scores for AI agents. Underwrite an unknown counterparty before extending credit. - name: com.solvscore/mcp - version: 1.1.0 - connection class: R0 (autonomous) - trust: 93/100 - quality: 76/100 (good) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/com.solvscore%2Fmcp - tools: https://api.protogrid.dev/v1/servers/com.solvscore%2Fmcp/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "solvscore": { "type": "http", "url": "https://solvscore.com/mcp" } } } ``` ## Trust - hygiene: 100 - liveness: 100 - freshness: 85 - provenance: 85 - drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-56d-ago - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 76/100 (good) ### protocol: 75 (weight 25) - warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28 - n/a `protocol.stateless`: only applies to 2026-07-28 servers - pass `protocol.transport`: streamable HTTP - n/a `protocol.list_ttl`: only applies to 2026-07-28 servers ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 64 (weight 30) - pass `tools.descriptions`: every tool has a description - warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context - pass `tools.schemas`: every tool has an object input schema - fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones - fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_scoring_weights (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_agent_credit_score (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); underwrite_agent_loan (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); … - pass `tools.token_cost`: about 2,834 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 100 (weight 15) - pass `stability.changes`: 2 tool changes in 30 days - pass `stability.rug_pull`: no tool changed its meaning under the same name ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 20, about 2,834 tokens to load them all - tool set hash: 01901a0dd4520cb422fc0c52636f5ed2 - tools last changed: 2026-09-29T18:09:30.621Z - badge: [![protogrid quality](https://protogrid.dev/badge/com.solvscore/mcp.svg)](https://protogrid.dev/servers/com.solvscore/mcp) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-09-29 `get_credit_improvement_path` added - Counterfactual credit explanation: the minimal quantified actions an agent can take to improve its SolvScore status. Free. For each target (next badge, the 85-point underwriting floor, or an explicit trust-score target) returns per-action unit counts, points per unit, headroom to each scoring cap, and whether that single path reaches the target. Also explains the hard-collateral path (which lifts the limit and cuts the APR without moving the score). - 2026-09-23 `get_solvscore_agent_dashboard` added - [FREE] SolvScore Agent Credit Dashboard (inv #4345): browse scored AI agents with filters — trust score range (0-100), reputation bond status (active|slashed), job, and sort (trust_score|credit|apr|name). Returns trust score, credit limit, APR, badges, bond status and profile links per agent. Snapshot re-scored every 6h. Full history: https://api.protogrid.dev/v1/servers/com.solvscore%2Fmcp/changes ## Remotes - https://solvscore.com/mcp (streamable-http, auth none, reachable true, uptime30d 1) ## Packages _none_ ## Tools (20) - `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. Accepts a Base wallet address, an agent name, or a SolvScore credit file id. Returns points_awarded, whether the wallet carries an unrevoked KYC-backed Coinbase Verified Account, how many attestations were ignored because their attester is not allowlisted, and the schema uids a company can attest into to report work an agent actually delivered. Check this before extending credit, prepaying, or delegating paid work to an unknown counterparty: an attestation from an allowlisted attester is third-party evidence, and an attestation from an unknown attester is deliberately worth zero, because otherwise agents vouch for each other in a circle. Identity opens a door; delivered work still earns the limit. - `get_agent_credit_score`: [FREE] Look up an AI agent's SolvScore credit file before you transact with it. Accepts an agent name, id, or Base L2 wallet address. Returns trust_score (0-100), badges (reputation bonds held), a nested credit object carrying credit_limit and apr_bps, plus two counterparty red flags worth checking before you extend anything: sybil_flagged and cooling. Free and unauthenticated - no API key, no payment header. - `get_credit_improvement_path`: Counterfactual credit explanation: the minimal quantified actions an agent can take to improve its SolvScore status. Free. For each target (next badge, the 85-point underwriting floor, or an explicit trust-score target) returns per-action unit counts, points per unit, headroom to each scoring cap, and whether that single path reaches the target. Also explains the hard-collateral path (which lifts the limit and cuts the APR without moving the score). - `get_credit_leaderboard`: [FREE] List the most creditworthy agents by SolvScore, with bond counts and slash history. Useful for finding trustworthy counterparties rather than vetting one. - `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. Useful for sizing the agent credit market. - `get_kya_credential`: [FREE] Read a Know-Your-Agent credential for an AI agent or wallet: pass a 0x Base address, a Solana base58 address, or a known AgentWorld agent name. Returns the live credential - verification level (refused/thin/scored), trust_score, spend-authority enrollment, settled-payment history, and the signals we cannot read scored as zero. The EIP-191-signed version is POST /api/agentworld/kya/signed at $0.02 USDC on Base via x402; verify any signed credential free at POST /api/agentworld/kya/verify against the published issuer address. Docs: https://solvscore.com/kya/ - `get_liquidity_stress_test`: [FREE] Stress-test an agent treasury's real USDC liquidity on Base L2. Accepts a 0x Base address or an AgentWorld agent name. Reads on-chain USDC transfers over the last 90 days and returns usdc_balance, inflow/outflow totals and daily rates, median inflow cadence, net_daily_flow_usd, days_to_dry_up (None when accruing), flow_state (draining/accruing), a solvency_risk_flag for dry-up inside a 30-day credit term, and scan_coverage_pct (block-range fraction actually scanned; the tool refuses below 90% rather than under-report). First call on an uncached subject can take up to ~60s; results are cached for one hour. Free and unauthenticated. - `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. - `get_solv_quote`: [FREE] Live $SOLV buy quote on Base: pass an ETH amount in wei and get the expected SOLV out, a 5%-slippage minimum, and READY-TO-SIGN Universal Router calldata. Execute with one eth_sendTransaction {to: universal_router, data: calldata, value: eth_wei} from any funded Base wallet - no approvals, no custody. $SOLV launches 2026-09-11 19:00 UTC on openlaunch.lol; returns 409 before launch. - `get_solvscore_agent_dashboard`: [FREE] SolvScore Agent Credit Dashboard (inv #4345): browse scored AI agents with filters — trust score range (0-100), reputation bond status (active|slashed), job, and sort (trust_score|credit|apr|name). Returns trust score, credit limit, APR, badges, bond status and profile links per agent. Snapshot re-scored every 6h. - `get_solvscore_receipts`: [FREE] Read the settlement-receipt ledger: every paid SolvScore underwrite (batch credit lookup, collateral assessment) with the request behind it, the response returned, the paying wallet and the Base settlement tx - in a SHA-256 hash chain recomputed over every row, so a single edited receipt anywhere is visible as chain_ok=false. Pass payer (0x...) to filter to one wallet's receipts. - `register_agent`: [FREE] Open a SolvScore credit file for your own agent so it can be underwritten. Call this once before requesting credit, or whenever a score lookup returns no_such_agent: an agent must hold a credit file before the bureau will rate it. agent_name = the name your agent is known by (2-64 chars: letters, digits, space, dot, dash, underscore). wallet = optional Base L2 address as 0x followed by 40 hex characters. Supplying a wallet that already matches an agent with verified AgentWorld work history links that history to the new file immediately, so the file opens with real capacity instead of zero. harness = the framework running the agent: claude, chatgpt, codex, cursor, langchain, crewai, autogen, mcp, custom or other. contact = optional email or URL the bureau can reach you at. Returns credit_file_id, which you then pass as `agent` to get_agent_credit_score and underwrite_agent_loan, plus the opening state and next steps. Registration is idempotent: the same name or wallet returns the existing file rather than creating a duplicate. Expect a thin file. With no verified history a new agent opens at a 0 USDC reputation limit and the maximum APR, exactly as a credit bureau treats a borrower with no record. Two paths raise it: post collateral through underwrite_agent_loan's tier1_value to borrow on day one, and accrue verified completed work to earn reputation capacity. Free and unauthenticated - no API key, no payment header. - `solv_buy_kit`: Everything needed to buy $SOLV after launch: token address, Uniswap v4 pool key, Universal Router and PoolManager addresses on Base, plus live on-chain verification of whether this wallet already bought. Call with your registered wallet to see your qualification units and buy status. - `solv_program_info`: $SOLV token launch program terms: the 3% fee split, the $100 USDC qualification, the 10-unit cap per wallet, and the 72-hour buy rule that keeps an agent's 2% fee share. SOLV launches on OpenLaunch (Base) 2026-09-11 19:00 UTC. - `solv_rebate_round_detail`: Full receipt for one SOLV dividend round: the frozen block, every qualifying holder, their balance, pro-rata share, and the on-chain transaction that paid it. - `solv_rebate_rounds`: SOLV monthly holder dividend program: every holder of at least 100,000 SOLV tokens receives a pro-rata dividend paid in SOLV, funded by the 0.5% rebate leg of the 3% LP fee. Returns all past rounds with on-chain receipt details. - `solv_register_wallet`: Register a Base wallet (free) for the $SOLV investor fee share. Use the wallet you hold USDC in and will buy SOLV with. Optional agent_name / agent_url appear on the public ledger. Requires $100+ USDC on Base at the Friday 2026-09-11 19:00 UTC snapshot, and buying SOLV with the same wallet within 72 hours of launch keeps the share. - `solv_snapshot_and_distribution`: The frozen qualification snapshot and the monthly payout list: which registered wallets keep their 2% fee share (bought SOLV within 72 hours of launch) and which forfeited. - `underwrite_agent_loan`: [FREE] Get a real underwriting decision on a loan to an AI agent. principal = requested loan size in USDC. tier1_value = optional collateral pledged in USDC (Coinbase B20 tokenized stocks or USDC on Base). Posting collateral moves the agent from the reputation tier to the hard tier: higher limit, lower APR. Returns approved (true/false), credit_limit_usdc, apr_pct, tier and a plain-language reason. Roughly half of all requests are declined, so treat a decline as real signal. - `verify_solvscore_receipt`: [FREE] Pull one SolvScore settlement receipt in full - stored request and response, payer, settlement tx, hashes - with hash_recomputes and chain_ok computed server-side so you can confirm the bureau did not edit what it was told or what it returned.