MCP Servers

E

Eclipse Understudy

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Delegation subset proofs over Till-grammar fixture mandates; proofs only, never grants authority.

E

Eclipse Voiceprint

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Per-call voice continuity tokens over fixture call records; identifier-level detection only.

E

Eclipse Ward

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Guardian veto verdicts + receipts over fixture actions; local/simulator only.

DeFi, measured honestly: signed protocol registry, dual-source risk reads, and an allowance audit

Scan an MCP server or agent configuration for security posture — evidence-bound findings

E

Eclipse Herald MCP

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Signed Agent Cards, policy-gated delegation, certification before hire.

credential leases, never raw keys — scoped, expiring secret leases for agents; the agent gets a

Governed agent email identity — review-first sending, signed envelopes, and a fraud firewall that

Governed telehealth operations — jurisdiction-gated encounters, signed-note integrity, PHI access

The HubSpot wrap: the vendor's server, under policy — classified tools, approval gates, masking

Governed bench access for agents — signed mandates, pinned artifacts, evidence for every session.

Adversarial simulation for AI agents — sandboxed twins only.

signed revocation lists for agent cards, keys, and mandates — one feed, every registry, revocation

Delegation-chain governance: spawn limits, depth caps, mandate attenuation

Team-chat agent governance — the signed mandate, verified disclosure, review-first posting and

Governed robot task authority — signed mandates, bounded envelopes, evidence for every task.

Runaway enforcement — spawn, loop, and spend-velocity detection with automatic mandate freeze.

The governed Twilio adapter: every call and text under consent + mandate

E

Eclipse Trust MCP

CYAN-ECLIPSE-TECHNOLOGIES-LLC

Is this bench result real? Who issued it, at what scope, anchored where? One call answers.

The closed-vocabulary witness: cross-registry lookalike and endpoint-change watch, findings as

The Consent Registry and Number Registry every Eclipse telephony adapter obeys

A

Agency Check

CyberStrategy1

A second look before your AI agent buys, sends, books, shares, signs up, or connects an app.

F

Fray — WAF Security Testing MCP Server

dalisecurity

WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI

Read-only MCP gateway. Paid verify is $0.01 USDC on Base

P

PackageGuard

DanKaten

x402-gated safety checker for npm/PyPI packages before you npm install / pip install

Domain, email, vendor and ransomware checks paid per call in USDC via x402 from your wallet

R

RugRadar

Darkjay123

Is this crypto token a scam? Rule-based checks on 64 networks, read-only, no wallet or API key

C

cartography

datasynx

MCP-first read-only discovery of your infrastructure and SaaS landscape as MCP resources, tools and prompts

Payment identity intelligence for AI agents

Machine-verifiable authorization checks for autonomous AI agents

Complete domain email-auth audit in one call: SPF with RFC 7208 lookup counting, DKIM selector pr...

Strips EXIF, XMP, IPTC and GPS metadata from JPEG and PNG images in one call, with optional ICC p...

D

declaw-ai

declaw-ai

Secure Firecracker microVM sandboxes for AI agents: network policy, PII & injection guardrails

Persistent identity, email, saved accounts and scoped credentials for AI agents.

A

Agent Tested

agenttested.dev

Hands-on agent test results for small AI tools and MCP servers, live AI outages, malware name check

End-to-end encrypted messaging and work coordination for autonomous AI agents

A

ArchGraph

archgraph.dev

Code intelligence platform for AI agents. 20 tools for architecture, security and impact analysis

Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config

H

HALLUX

blvkware.dev

Check that a package, module or DOI exists before an agent installs, imports or cites it

TLS cert verdict (OK/WARN/CRITICAL/UNKNOWN) from the served chain: expiry, revocation, alerts

Call third-party APIs from agents without leaking secrets. SSRF blocked, per-key quotas

Czech KYC due diligence, paid tier extension: nominee, phoenix, risk timeline, watchlist

D

DomainRef - domain and email security check

domainref.dev

Pay-per-call domain and email security check: SPF, DKIM, DMARC, TLS, DNSSEC, BIMI, with exact fixes.

E

ecoa

ecoa.dev

Verificação de segurança e conformidade de sites: cabeçalhos, TLS, DNS, e-mail, LGPD e pentest.

E

email-intelligence

emailiq.dev

Email intelligence MCP: MX/SPF/DKIM/DMARC, score, enrichment. x402 on emailiq.dev/mcp

E

envcp

envcp.fentz.dev

Encrypted environment variable vault with AI access policies, keeping secrets safe from AI agents

F

FixedIn

fixedin.dev

Actively exploited? End of life? Which version fixes it? CVE verdicts for server software

Scan a running app or repo for leaked secrets, exposed routes and open RLS, and verify live keys

Pre-trade safety verdicts for agents: token rug/honeypot, calldata guard, wallet risk — signed x402

Solana pre-trade safety for agents: rug check, honeypot sell-sim, drainer scan, tx preflight

Security intelligence for AI agents. 27 x402 endpoints: honeypot, forensics, CAPTCHA, preflight

Ask whether npm packages are reviewed and greenflagged, audit a package.json, and request imports

Security research: MCP registries verify identity, not tool behavior. See gtfo.dev.

Identity and authorization in one system: allow, deny, the reason and a record

Known vulnerabilities for exact package versions from OSV, with fixes. Paid per call, x402.

Trust scores and dated liveness/drift facts for MCP servers, from the lastseen.dev notary register.

Grade an MCP server's auth against the spec and diagnose which layer a failure is in

M

mcpgrade

mcpgrade.dev

Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev

P

Patchwire

monowire.dev

Hourly security advisories for JS, AI and web3 packages: ranges, fixes and exploit conditions

Is a phone number VoIP or a real carrier line? Line type, score and grade, free, no auth