"Installing MCP (Minecraft Coder Pack) servers into an IDE" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Signed, traced record of what an npm package or file attempts when run, network included. No key.
Source-linked evidence and reusable local checks for agent integration and review. Explore seven free evidence packs and three executable products, with questions, demonstrations and direct preview/purchase links: https://varexis.tech/index-packs Agent Tool Admission & Permission Control — GBP 49 + applicable VAT, one time. Supply local JSON declarations for GitHub, Playwright, Notion or Slack. The Node.js24 executable compares actions, resources, recipients, authority and inventory changes, returning a structured gap report. Free demonstration: https://varexis.tech/varexis-index/examples/agent-tool-admission/DEMONSTRATION.txt Agent Audit & Evidence Coverage — GBP 79 + applicable VAT, one time. Supply a declared event/evidence inventory. The local executable checks identity/authorization/action/outcome references and missing capture, export, retention or recovery coverage. Free demonstration: https://varexis.tech/varexis-index/examples/agent-audit-coverage/DEMONSTRATION.txt Each standalone licence is for one buyer or legal entity's internal staff, agents and CI use. No customer declarations are uploaded. No redistribution, external API resale, updates, monitoring or support SLA. Existing snapshot offers and subscriptions do not include these two licences. Checks concern supplied declarations; no live-permission inspection, enforcement, proof that records exist or certification. Seven complete evidence packs stay free: GitHub + Playwright permission boundaries; Notion + Slack access/data handling; GitHub/Slack/Cloudflare audit/export coverage; three dated Next.js advisory assertions; SonarQube/Snyk/Semgrep scanner trust; telemetry redaction gaps; GitHub release acceptance. These are dated documentation reviews or frozen source assertions, not independent tool tests or current safety assessments. Existing GBP 5 Single Request saves a version-bound public pack, or delivers the original Agent Tool Evaluation & Integration executable kit. GBP 19 Evidence Receipt also adds an unsigned delivery record. Plus applicable VAT. Eligible Research (GBP 29/month + VAT) and Developer/API (GBP 149/month + VAT) subscriptions retain their existing limits; an eligible pack or original kit uses one query. No continual refresh or permanent-retention promise. Public MCP discovery is free, unauthenticated and read-only: https://varexis.tech/mcp Connect: https://varexis.tech/index-connect Purchase or recover: https://varexis.tech/index-access Agent contract: https://varexis.tech/varexis-index/agent-payments.json Hosted Stripe and compatible authorised MPP/Stripe SPT purchasing use separate authenticated paths. Agents require owner spending authority for the exact tax-inclusive quote and required provider authentication; not every agent or wallet is compatible. Retrieve saved purchases or use eligible entitlements before buying. Recover uncertain payment with the original key and matching result endpoint; retain the original payment credential for supported retries. Never buy again to repair uncertain delivery. Payment adds no fresh investigation, independent assurance or deployment approval.
Check before money moves. Lorg Check tells an AI agent, or you, whether a token is a trap or an address is unsafe to pay, on Base and Ethereum. In live tests on new launches it blocked traps that GoPlus and Honeypot.is missed. Call check_token before buying or swapping into a token: it simulates a real buy and sell-back through the token’s own pool, reads what the creator can still do, who can pull the liquidity, and whether the creator was paid by a wallet behind earlier rugs. Call check_address before sending funds: sanctions, scam labels, EIP-7702 sweepers and address-poisoning look-alikes. Every answer is signed and says proceed, limit_exposure or do_not_proceed, with a one-line summary to show the user. Free key by GitHub sign-in, or connect with an API key.
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
Sourced privacy answers: how private an app is, tool picks, app swaps, de-Googling, breaches.
Check an npm or Python package, or a package.json, for vulnerabilities and upkeep.
Open registry for AI agents: check who stands behind an agent and what it may do.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.
Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.
Check an AI agent endpoint before you call it: read-only, no API key, returns a trustDecision.
Verify an AI agent artifact: schema, emptiness, provenance and mandate authority, Ed25519-signed.
Block an action that a signed mandate does not permit, at the moment the action happens. Checks amount, payee, audience, currency, window and intent in fixed order; 100 checks a day free, then 0.005 USDC per call over x402 on Base mainnet.
Check an npm/PyPI package before an AI agent installs it: 5 focused supply-chain tools.
Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.
Domain, email and web audits for AI agents: DNS, RDAP, TLS, SPF, DMARC, DKIM, MTA-STS, security headers and cookies, with graded findings and an A-F score. Requires a Bearer token.
Vet an agent skill before you install it: structure, triggers, secrets.
Runs an eight-stage isolation test against your staging Supabase and issues a signed attestation. Needs a RowAttest API key: Authorization: Bearer rak_... (create one on the API keys page in the app).
Verify an artifact an AI agent produced — schema, emptiness, provenance and mandate authority — before you accept the work or pay for it. Ed25519-signed and verifiable without this service; 20 checks a day free, then 0.005 USDC per call over x402.
Review supplied evidence of actor identity, principal authorization, tool scope and intended action before an agent acts. Returns missing evidence and review guidance; enforcement belongs to the caller integration. Two MCP-native free trial attempts per network for the campaign, shared daily capacity. No action authorization or identity certification.
