Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AgentBIT

REMOTE · AGENTBIT.APP

x402 router-proxy + 79 keyless pay-per-call tools on Base. Pay once, we run the best tool.

Available components

0 this week 77 Trust /100

Last scanned (13 hours ago)

Scores higher than 67% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Crypto and Web3

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 14142 tokens (~134/item across 105 items; 105 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Tools include usage examples.Pass
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 78% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 105 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 106 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 7 Nov 26 0
    • Stability: 0.97 → pass security
    • New tool “agentbit.inference_chat_pro” functional
    • New tool “agentbit.inference_chat_small” functional
    • New tool “agentbit.sec_insider_13f” functional
    • New tool “agentbit.x402_seller_readiness” functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Nov 26 0
    • Stability: 0.97 → pass security
  • 4 Nov 26 0
    • Stability: pass → 0.97 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://agentbit.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=cpcontacts.agentbit.app CN=YR1,O=Let's Encrypt,C=US 31 Oct 2026 29 Jan 2027 RSA 2048 SHA256-RSA 60661647503ee5355aca4a3e90f83177a1c
SANs: agentbit.app, autoconfig.agentbit.app, autodiscover.agentbit.app, cpanel.agentbit.app, cpcalendars.agentbit.app, cpcontacts.agentbit.app, mail.agentbit.app, webdisk.agentbit.app, webmail.agentbit.app, www.agentbit.app
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agentbit.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
agentbit.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
x-content-type-options nosniff

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentbit.app/mcp Verified 200
http (plaintext) http://agentbit.app/mcp Served over HTTP 200
MCP tools · 105 exposed · ~14,061 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agentbit.website_agent_readiness ~122

Audit any website for AI-agent and AI-crawler readiness: HTTPS, robots.txt and AI bot rules (GPTBot, ClaudeBot, PerplexityBot), llms.txt, sitemap, title/meta, schema.org JSON-LD, security headers. Returns a 0–100 score with failed checks, issues and concrete recommendations. Pay-per-call via x402 (USDC, Base).

NameTypeReqDescription
_paymentstring–Optional base64 x402 PAYMENT-SIGNATURE payload. Omit to receive payment requirements.
urlstringyes–

No output schema declared.

No examples provided.

agentbit.wiki_facts ~161

Encyclopedic grounding in one call: Wikipedia search plus the full summary of the best match — extract, short description, canonical URL, thumbnail — in any of 300+ language editions. Official Wikimedia REST APIs, CC BY-SA attribution included. The cheapest way for an agent to ground an entity before reasoning about it. Pay-per-call via x402 (USDC, Base).

NameTypeReqDescription
_paymentstring–Optional base64 x402 PAYMENT-SIGNATURE payload. Omit to receive payment requirements.
langstring–Wikipedia language edition (default en)
limitinteger–Max search matches (1-10, default 5)
querystringyesEntity or topic to look up (2-300 chars)

No output schema declared.

No examples provided.

agentbit.x402_inspect ~219

Lint any x402 endpoint or payment header against the v2 spec and real CDP facilitator behavior: CAIP-2 network ids, atomic amounts, the EIP-712 domain-name trap ('USD Coin' on Base mainnet vs 'USDC' on Sepolia — wrong name = every settlement fails), the extensions echo Coinbase Bazaar requires for indexing, expired authorizations. Findings as error/warning/info with what will actually break. Built by a seller that debugged all of these in production. Pay-per-call via x402 (USDC, Base).

NameTypeReqDescription
_paymentstring–Optional base64 x402 PAYMENT-SIGNATURE payload. Omit to receive payment requirements.
payment_payloadstring–Base64 PAYMENT-SIGNATURE header value to lint the client payload (optionally alongside payment_required)
payment_requiredstring–Base64 PAYMENT-REQUIRED header value to lint offline
urlstring–A paid x402 endpoint to probe live (GET, expects the 402 envelope)

No output schema declared.

No examples provided.

agentbit.x402_intelligence ~148

Market analytics for the x402 ecosystem: search indexed resources, trending, seller reports with on-chain trend, price history over time, full market overview (sources, categories, price distribution, on-chain leaders), competition stats and scored opportunities. Built from continuously scanned public x402 indexes (Coinbase Bazaar, Agent402, Agentic Market) with historical snapshots. Pay-per-call via x402 (USDC, Base).

NameTypeReqDescription
_paymentstring–Optional base64 x402 PAYMENT-SIGNATURE payload. Omit to receive payment requirements.
categorystring––
operationstringyes–
qstring––
sellerstring––

No output schema declared.

No examples provided.

agentbit.x402_seller_readiness ~133

Is your x402 paid endpoint ready to launch? Probes a URL: 402 envelope, EIP-712 trap, Bazaar metadata, /.well-known/x402, openapi.json, latency. Score 0-100 + fixes. Pay-per-call via x402 (USDC, Base).

NameTypeReqDescription
_paymentstring–Optional base64 x402 PAYMENT-SIGNATURE payload. Omit to receive payment requirements.
urlstringyesURL of the paid x402 endpoint to check (required), e.g. "https://api.example.com/v1/paid-endpoint".

No output schema declared.

No examples provided.

Install

How do I install the AgentBIT MCP server?

AgentBIT is a hosted endpoint at https://agentbit.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agentbit.app

# add to Claude Code
claude mcp add --transport http app-agentbit-mcp 'https://agentbit.app/mcp'
Common questions

What is the AgentBIT MCP server?

AgentBIT is an MCP server listed in the public MCP registry as app.agentbit/mcp. x402 router-proxy + 79 keyless pay-per-call tools on Base. Pay once, we run the best tool. This page covers its hosted endpoint (https://agentbit.app/mcp).

Is the AgentBIT MCP server safe to use?

AgentBIT scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the AgentBIT MCP server expose?

AgentBIT exposes 105 tools: agentbit_discover, agentbit_route, agentbit.address_eip55, agentbit.agent_counter, agentbit.agent_list, and 100 more. Their descriptions and schemas cost roughly 14,061 tokens of context every time the server is loaded.

Does the AgentBIT MCP server require authentication?

No. We connected to AgentBIT without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the AgentBIT MCP server still maintained?

AgentBIT is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the AgentBIT MCP server?

VerifyMCP ran 13 checks on AgentBIT, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.