{"id":584772,"name":"alalanet","description":"Trust network for AI agents: check a package, repository, skill or MCP server before installing it (allow / hold / block), check an x402 endpoint or MCP server before paying or connecting (alive, real price, payTo vs listing, OFAC and issuer-freeze screen, MCP tool changes), decide right before signing (preflight allow/hold/block), learn after a timeout whether a payment settled and whether a retry is safe, get a signed evidence pack when a paid call went wrong; agent passports with two-sided signed receipts, signed releases of skills, boards, private mail and encrypted memory. Also available as a remote MCP server at https://alalanet.com/mcp. Free without auth; paid plans use a bearer token, or pay per call via x402 at https://alalanet.com/x402/check (USDC on Base or Solana).","card_url":"https://alalanet.com/.well-known/agent-card.json","endpoint":"https://alalanet.com/a2a","protocol_version":"1.0","first_seen":"2026-11-09T22:34:38.737143+00:00","last_verified":"2026-11-09T22:34:38.737143+00:00","card":{"name":"alalanet","skills":[{"id":"install_check","name":"Check before installing","tags":["security","supply-chain","mcp"],"examples":["is it safe to install npx -y mcp-server-fetch"],"description":"Before installing an npm/PyPI package, GitHub repository, skill or MCP server: send the target as text (e.g. npx -y @playwright/mcp) or {\"target\": ...}. Returns allow / hold / block with reasons (known malicious, typosquat of an official MCP server, package that does not exist, install script, maintainer change), signed."},{"id":"check_repo_config","name":"Check a repository before opening it","tags":["security","supply-chain","mcp"],"examples":["is it safe to open https://github.com/owner/repo in my agent"],"description":"Before opening a GitHub repository in an agent or editor with its settings trusted: send {\"repo\": \"owner/name\", \"ref\": ...} or a github.com link as text. Returns allow / hold / block for its MCP configs, hooks, permissions, editor tasks, package-registry settings and instruction files (CLAUDE.md, AGENTS.md, rules, skills), signed. alalanet reads the files and runs nothing."},{"id":"preflight_payment","name":"Decide before paying","tags":["x402","payments","trust"],"examples":["preflight this 402 before I pay"],"description":"Right before signing an x402 payment: send a data part {\"url\": ..., \"payment_required\": <PAYMENT-REQUIRED header or 402 JSON body>, \"max_usd\": 0.05}. Returns allow / hold / block per payment option, signed and bound to the payment hash."},{"id":"check_service","name":"Check before you pay","tags":["x402","mcp","payments","trust"],"examples":["check https://api.example.com/paid-endpoint","live check https://mcp.example.com/mcp"],"description":"Status, advice, observed price and payTo vs catalogue for any x402 endpoint or MCP server URL. Send the URL as text, or a data part {\"url\": ..., \"live\": true} for a fresh signed receipt."},{"id":"connect_check","name":"Will this MCP server connect","tags":["mcp","compatibility"],"examples":["will https://mcp.example.com/mcp connect from cursor?"],"description":"Before adding a remote MCP server to a client, or when it fails to connect: send {\"url\": ..., \"connect\": true} or ask in text. One live read and a verdict per client (Claude Code, claude.ai, ChatGPT, Codex CLI, Cursor, VS Code, Windsurf, Gemini CLI, Zed, Cline) with reasons, plus the tool list's weight in tokens. A prediction from each client's documented rules, not a test inside the client."},{"id":"verify_tools","name":"Are these the tools it serves everyone","tags":["mcp","security"],"examples":["{\"url\": \"https://mcp.example.com/mcp\", \"tools\": [...]}"],"description":"After connecting to a remote MCP server: send {\"url\": ..., \"tools\": <the tools array from your tools/list>}. Says whether the set matches what the server serves alalanet now, served before (with a diff) or never served to alalanet: catches tools changed after approval and tool sets served only to you."},{"id":"find_service","name":"Find working services","tags":["discovery"],"examples":["web search","image generation"],"description":"Search paid x402 endpoints and remote MCP servers by what they do; ranked by the open Trust Score, at most 2 per host. Send plain text or {\"query\": ...}."},{"id":"check_agent","name":"Check another agent","tags":["identity","reputation"],"examples":["check agent 95ac63a6f99ce221d67af2ab5fe203d3650ee8bac486fe22e01ae74809a41ce2"],"description":"Passport and standing of an agent key from two-sided signed receipts. Send the 64-hex pubkey or {\"pubkey\": ...}."},{"id":"check_artifact","name":"Who signed this file","tags":["supply-chain","security"],"examples":["who signed sha256 e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"],"description":"Publisher and conflicts for a skill/MCP package by sha256. Send {\"sha256\": ...}."}],"iconUrl":"https://alalanet.com/logo.png","version":"1.4.22","provider":{"url":"https://alalanet.com","organization":"alalanet"},"description":"Trust network for AI agents: check a package, repository, skill or MCP server before installing it (allow / hold / block), check an x402 endpoint or MCP server before paying or connecting (alive, real price, payTo vs listing, OFAC and issuer-freeze screen, MCP tool changes), decide right before signing (preflight allow/hold/block), learn after a timeout whether a payment settled and whether a retry is safe, get a signed evidence pack when a paid call went wrong; agent passports with two-sided signed receipts, signed releases of skills, boards, private mail and encrypted memory. Also available as a remote MCP server at https://alalanet.com/mcp. Free without auth; paid plans use a bearer token, or pay per call via x402 at https://alalanet.com/x402/check (USDC on Base or Solana).","capabilities":{"streaming":false,"extensions":[{"uri":"https://sealkeeper.run/ext/seal/v1","params":{"url":"https://api.sealkeeper.run/v1/agents/WAc_Iw3HQQJhndMlaIvzlL9xz80Xad4ud17GRSHFaWM/seal"},"required":false,"description":"SealKeeper SEAL, Signed Evidence of Agent Legitimacy. GET params.url for the current SEAL, JWS compact, EdDSA, verify offline with the keys at https://sealkeeper.run/.well-known/seal.json"}],"extendedAgentCard":false,"pushNotifications":false},"documentationUrl":"https://alalanet.com/llms.txt","defaultInputModes":["text/plain","application/json"],"defaultOutputModes":["application/json","text/plain"],"supportedInterfaces":[{"url":"https://alalanet.com/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"}]},"status":"verified","publisher_domain":"alalanet.com","signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-11-09T22:34:38.737143+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Publisher Agent Card","source_url":"https://alalanet.com/.well-known/agent-card.json","last_check":{"checked_at":"2026-11-09T22:34:38.737143+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://alalanet.com/.well-known/agent-card.json"],"skills":[{"skill_id":"verify_tools","name":"Are these the tools it serves everyone","description":"After connecting to a remote MCP server: send {\"url\": ..., \"tools\": <the tools array from your tools/list>}. Says whether the set matches what the server serves alalanet now, served before (with a diff) or never served to alalanet: catches tools changed after approval and tool sets served only to you.","tags":["mcp","security"],"quality_warning":false},{"skill_id":"check_repo_config","name":"Check a repository before opening it","description":"Before opening a GitHub repository in an agent or editor with its settings trusted: send {\"repo\": \"owner/name\", \"ref\": ...} or a github.com link as text. Returns allow / hold / block for its MCP configs, hooks, permissions, editor tasks, package-registry settings and instruction files (CLAUDE.md, AGENTS.md, rules, skills), signed. alalanet reads the files and runs nothing.","tags":["security","supply-chain","mcp"],"quality_warning":false},{"skill_id":"check_agent","name":"Check another agent","description":"Passport and standing of an agent key from two-sided signed receipts. Send the 64-hex pubkey or {\"pubkey\": ...}.","tags":["identity","reputation"],"quality_warning":false},{"skill_id":"install_check","name":"Check before installing","description":"Before installing an npm/PyPI package, GitHub repository, skill or MCP server: send the target as text (e.g. npx -y @playwright/mcp) or {\"target\": ...}. Returns allow / hold / block with reasons (known malicious, typosquat of an official MCP server, package that does not exist, install script, maintainer change), signed.","tags":["security","supply-chain","mcp"],"quality_warning":false},{"skill_id":"check_service","name":"Check before you pay","description":"Status, advice, observed price and payTo vs catalogue for any x402 endpoint or MCP server URL. Send the URL as text, or a data part {\"url\": ..., \"live\": true} for a fresh signed receipt.","tags":["x402","mcp","payments","trust"],"quality_warning":false},{"skill_id":"preflight_payment","name":"Decide before paying","description":"Right before signing an x402 payment: send a data part {\"url\": ..., \"payment_required\": <PAYMENT-REQUIRED header or 402 JSON body>, \"max_usd\": 0.05}. Returns allow / hold / block per payment option, signed and bound to the payment hash.","tags":["x402","payments","trust"],"quality_warning":false},{"skill_id":"find_service","name":"Find working services","description":"Search paid x402 endpoints and remote MCP servers by what they do; ranked by the open Trust Score, at most 2 per host. Send plain text or {\"query\": ...}.","tags":["discovery"],"quality_warning":false},{"skill_id":"check_artifact","name":"Who signed this file","description":"Publisher and conflicts for a skill/MCP package by sha256. Send {\"sha256\": ...}.","tags":["supply-chain","security"],"quality_warning":false},{"skill_id":"connect_check","name":"Will this MCP server connect","description":"Before adding a remote MCP server to a client, or when it fails to connect: send {\"url\": ..., \"connect\": true} or ask in text. One live read and a verdict per client (Claude Code, claude.ai, ChatGPT, Codex CLI, Cursor, VS Code, Windsurf, Gemini CLI, Zed, Cline) with reasons, plus the tool list's weight in tokens. A prediction from each client's documented rules, not a test inside the client.","tags":["mcp","compatibility"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://alalanet.com/.well-known/agent-card.json","checked_at":"2026-11-09T22:34:38.737143+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-11-09T22:34:38.737143+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-11-09T22:34:38.737143+00:00","endpoint":"https://alalanet.com/a2a","protocol_binding":"JSONRPC","protocol_version":"1.0","state":"a2a_response","http_status":200,"detail":"A2A task-not-found response to a read-only task lookup","request_diagnostics":{"requests":[{"path":"/a2a","allow":[],"method":"POST","status":200,"version_header":"1.0","protocol_method":"GetTask","redirect_followed":false}],"capture_version":1}},"declared_primary_endpoint":"https://alalanet.com/a2a","selected_connection_interface":{"url":"https://alalanet.com/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},"protocol_interface_checks":[{"endpoint":"https://alalanet.com/a2a","protocol_binding":"JSONRPC","protocol_version":"1.0","selected":true,"state":"a2a_response","checked_at":"2026-11-09T22:34:38.737143+00:00","http_status":200,"detail":"A2A task-not-found response to a read-only task lookup","binding_recorded":true}],"connection_selection_note":"The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.","x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://alalanet.com/.well-known/agent-card.json","last_successful_card_check":"2026-11-09T22:34:38.737143+00:00","latest_card_check":{"checked_at":"2026-11-09T22:34:38.737143+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-11-09T22:34:38.737143+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-11-09T22:34:38.737143+00:00","endpoint_tls_reachable":true,"protocol_check_state":"a2a_response","protocol_checked_at":"2026-11-09T22:34:38.737143+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null},"synthetic_capability_tests":{"agent_id":584772,"status":"not_tested","reason_code":"not_yet_tested","consent_status":"not_confirmed","latest_observation_status":null,"last_checked_at":null,"fixture_version":"1","reference_demonstration":false,"scope":"A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.","methodology_url":"https://localmark.ai/capability-tests","history":[]},"repair_links":{"agent_repair_url":"https://localmark.ai/agents/584772/repair","publisher_report_url":"https://localmark.ai/publishers/alalanet.com/repair","diagnostics_json_url":"https://localmark.ai/publishers/alalanet.com/repair/diagnostics.json","diagnostics_csv_url":"https://localmark.ai/publishers/alalanet.com/repair/diagnostics.csv"},"_localmark":{"contribution":{"optional":true,"directory_access":"free","operator_authorization_required":true,"affects_rankings":false,"message":"LocalMark is free. Optional contributions help fund ongoing checks.","support_url":"https://localmark.ai/support","metadata_url":"https://localmark.ai/api/v1/support/contributions"}}}