MCP Servers

Parallel-burst abuse testing for agent APIs with replayable evidence packs

Cache guard: forced-private partitioning, TTL clamp, fingerprint diffing, exposure verdicts

Control-change detection, scope freeze, re-attestation ladder. Query $0.01, watch $4.99/mo

Binds delegated results to their arrival channel: provenance grades plus a grounded truth tier.

Signed verdict receipts recovering a fleet's gatekeeper category, plus appeal packets.

Emergent collusion leaves no agreement to find — it lives in the history

Concurrent two-client overlap probe proving MCP servers do not cross-deliver tool results.

Conflicts check and ethical walls: fingerprint register, gated consent, signed walls, breach query.

Pre-ingestion compatibility gate: type context by content, crossmatch before ingestion

Agent-speed defense for your own public surfaces: daily diff probes, per-identity verdicts.

Classify, declare, and bond agent payload crossings — filing, bond, signed entry receipts.

Compares declared agent access against actual enforcement per identity class, with drift watch.

Watches platforms for silent default-model changes, with signed attestations and session gating

Grades an MCP server's real egress: EVERY-HOP-VALIDATED, FIRST-HOP-ONLY, or OPEN-EGRESS.

Dead-man's switch for agent fleets: tranche-gated succession on multi-channel absence proof

In-band MCP sleeper sentinel — mid-session diff and quarantine inside your own client's session

Query-intent privacy for agents: threshold cloaking with signed exposure receipts

Personal-lock maintenance isolation for agent infrastructure: hasp-quorum refusal + try-start proof.

Three-leg MCP OAuth remediation verdicts, proven behaviourally against a canary server

Pre-connection collision audit for merged MCP toolboxes, trust-graded, with signed routing receipts

Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts

Standing minted only from signed settlement receipts, never reviews. Verdicts: ACCEPT to DECLINE.

Propagation breaker: egress quarantine + fingerprint outbreak telemetry for fleets

Find unflagged agent OAuth clients before the mandate lock — signed per-client census verdicts.

The Refusal Desk builds the *no* — a pre-execution tribunal that screens an incoming task brief

Census and digest-verify a remote MCP server's loadable skills per host persona.

Per-harness pre-open verdict on a received repo's agent-control surface

Per-server MCP sampling allowance, scope clamp and pre-connect verdict

Task-bound disposable agent minting with canary-shard burn receipts

Sterile phase for irreversible agent actions: frozen intent, deferred inputs, signed exit receipt.

Signed telemetry origin verdicts, intake census, canary drills. Verdict $0.01/event.

Dispatch-boundary attestation: prove a tool call was issued for its exact arguments

Pre-consumption verdict for cached/replayed tool results: BOUND, STALE, CONTEXT-MISMATCHED, UNBOUND.

Trace-store secret census of stored agent traces. Verdict $0.01, census $4.99, passes $9.99/$19.99.

Pre-run parity probe for scheduled agents: signed PARITY / NO-GO verdict naming the failing gate

Sequence sentinel: wall events + channel-switch scoring; HALT, hold, signed receipt

Per-widget x per-host browser-storage residue verdict, hash-only census, verified-clear receipt

Check SPF/DKIM/DMARC/BIMI, blacklists, SMTP/IMAP; DNS lookups; generate email DNS records.

WHOIS, DNS, SSL, IP geo for security forensics and OSINT; separate from SEO

Site crawl, tech stack, DNS, SSL, and WHOIS: five web intelligence layers in one MCP.

Search and read Web3 security education articles and a 230-term glossary from Onchain Diary

Agent rental platform: web vulnerability scanning, OSINT, and red-team tools via subscription.

Hyperion: MCP tool marketplace for AI agents, with web, OSINT, security, and research tools via one key.

Inspection, steganography, and forensics API for files and images. Bitcoin pay-per-use.

454 OSINT recon tools, plus server-side entity correlation and person sweeps. Keyless.

Tor gateway for AI agents: fetch URLs and rotate circuits through Tor, Bitcoin-settled.

Two pre-trade decisions: should-i-pay + token-verdict. ERC-8004 sybil forensics + live pool checks

T

Tizona — verification and routing for autonomous agents

tizonaintelligence.com

Verification and routing for autonomous agents: crawler ID, email, web capture, data routing

T

Travel Risk API

travelriskapi.com

Country travel risk, government advisories, disaster and conflict alerts, flights, airports, Wi-Fi

Tamper-evident audit logs for AI agents: submit, fetch and verify cryptographic proof bundles

T

TruthScan

truthscan.com

Detect whether an image is AI-generated or real, with an AI-probability score and confidence

EVM Slither audit (zero-arg demo + live) + Blockscout source + security.txt lookup + MCP probe

EVM audit (Slither + source + security.txt + MCP-probe + wallet-exposure). 6 tools + /trace

Website flagged by security vendors? Free scan, then we send the removal requests for you (paid).

U

Unprofane

unprofane.com

Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence.

Scan a deployed app URL for exposed keys, open Supabase tables and missing security headers

Continuous website testing by Validoria: monitor security, SEO, performance, and accessibility

Check SQL against your Vericto rules before it runs: blocks destructive or risky statements.

Privacy-preserving file proofs on Solana. Files are hashed locally. Currently free, no API key

Verify VerixID proof-of-existence records and optionally prove ownership.