"MCP servers for reducing hallucinations while coding" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Pre-trade token safety check for AI agents. Simulates a sell before you buy, then returns one low/medium/high/unknown verdict with the signals behind it: sellability, buy/sell tax, liquidity depth, pair age, same-ticker impersonation, owner powers from bytecode. Ethereum, BSC, Base, Solana. Fail-closed - a check that cannot run answers unknown, never low. Publishes its own measured error rate with the benchmark harness in the repo. Free, no signup, no API key, MIT.
Technology intelligence feed for AI agents: tech stack, compliance, security.
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.
VPN, proxy, Tor, hosting and CDN detection for any IP address, from the VPNDetection API.
Preflight for AI agents, signed: one call; wallet, domain, IP abuse, package checks and CVEs.
Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.
Shared second brain for any AI with agent permissions
Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.
DMARC analytics for AI assistants: SPF/DKIM, compliance, anomalies, p=reject readiness, onboarding.
Free, no-API-key network lookups for AI agents — IP geolocation, DNS, WHOIS, HTTP and SSL/TLS certificate checks, and full domain health reports.
Free website privacy scanner for pre-consent cookies, trackers, consent, policy, and HTTPS/TLS.
Send contracts for e-signature, track signing, get signed PDFs and audit trails, verify any PDF.
Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
Audits any Base/EVM address for bytecode risk, proxy patterns, honeypot selectors, and balance.
Real-time RFC 5321 email verification with direct TCP port 25 SMTP mailbox checks, disposable/burner firewall (100k+ domains), and bulk cleaning for AI agents. Sub-140ms latency with zero email delivery.
Collision-first MCP diagnostics for MCP, API, webhook and agent failures. Returns structured evidence, bounded repair guidance, agent compatibility checks and safe recovery routing.
AskYourStack connects Claude to your Linux server and to Google Search Console over MCP. On a server, a small open-source agent (Apache-2.0, reproducible builds) dials out to AskYourStack; no SSH key or password is stored. Claude can then set up a raw VPS, install Magento or WordPress, read logs and fix errors, take backups and snapshots, harden the server, scan for malware and move a site to a new server. It runs as the Linux user who owns the sites by default, or as root when the user chooses
Set up human approval for your AI agents' tool calls.
Hosted login, teams, billing and feature flags for your SaaS app, set up by your AI assistant.
