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.

OnChainDiligence

REMOTE · MCP.ONCHAINDILIGENCE.COM

Payment evidence and policy preflight, plus paid sanctions and company Evidence Provider checks.

0 this week 84 Trust /100

Last scanned (12 hours ago)

Scores higher than 89% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Finance and Payments

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 Security80
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2042 tokens (~97/item across 21 items; 21 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage74
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 23% 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 21 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.

  • 18 Oct 26 0
    • Tool “diligence” rewrote its description, which is the text the model reads security
    • Tool “inspect_payment” rewrote its description, which is the text the model reads security
    • Tool “preflight_payment” rewrote its description, which is the text the model reads security
    • Tool “screen_wallet” rewrote its description, which is the text the model reads security
  • 17 Oct 26 0
    • Tool “diligence” rewrote its description, which is the text the model reads security
    • Tool “inspect_payment” rewrote its description, which is the text the model reads security
    • Tool “preflight_payment” rewrote its description, which is the text the model reads security
    • Tool “screen_wallet” rewrote its description, which is the text the model reads security
  • 28 Sept 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
  • 27 Sept 26 0
    • Stability: 0.97 → pass security
  • 26 Sept 26 0
    • Stability: pass → 0.97 functional
  • 25 Sept 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
  • 13 Sept 26 0
    • Tool coverage: 33% → 23% ▼ functional
    • Schema quality: fail → pass ▲ functional
    • New tool “inspect_bridge” functional
    • New tool “inspect_staking” functional
    • New tool “observe_bridge” functional
    • New tool “observe_staking” functional
    • New tool “preflight_bridge” functional
    • New tool “preflight_staking” functional
  • 12 Sept 26 0
    • Tool coverage: 63% → 33% ▼ functional
    • Schema quality: 138 → 108 ▲ functional
    • Schema quality: excellent → good functional
    • New tool “inspect_allowance” functional
    • New tool “inspect_swap” functional
    • New tool “observe_allowance” functional
    • New tool “observe_swap” functional
    • New tool “preflight_allowance” functional
    • New tool “preflight_swap” 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 5 Nov 2026 · Probed https://mcp.onchaindiligence.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.onchaindiligence.com CN=YR2,O=Let's Encrypt,C=US 22 Oct 2026 20 Jan 2027 RSA 2048 SHA256-RSA 5a4cd477183e90500ac33bb78c4bad05043
SANs: mcp.onchaindiligence.com
CN=YR2,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA 4ebd24947e24d394802d84a52fd5b319
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 mcp.onchaindiligence.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
onchaindiligence.com. absent 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
strict-transport-security max-age=63072000

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.onchaindiligence.com/mcp Verified 200
http (plaintext) http://mcp.onchaindiligence.com/mcp HTTPS enforced 308 https://mcp.onchaindiligence.com/mcp
MCP tools · 21 exposed · ~2,042 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
diligence ~135

Combined counterparty due diligence in one call: an exact OFAC SDN digital-currency-address screen of an EVM wallet AND a UK Companies House KYB lookup (status, type, PSC / beneficial owners), in parallel. Returns both independent results plus an explicit disclaimer that no verified link between the wallet and the company is established by the data. SDN only; a non-match is not clearance. Refused before payment if current sanctions data is unavailable.

NameTypeReqDescription
companystringyesUK Companies House registration number to verify
walletstringyesEVM wallet address (0x + 40 hex) to sanctions-screen

No output schema declared.

No examples provided.

get_receipt ~126

Look up a public OCD receipt by its exact receipt_id (format "OCD-RCP-XXXX-XXXX-XXXX-XXXX"). Free, no payment. Returns the complete signed receipt envelope, or a structured not-found/unavailable reason -- never a guess. A private (unpublished) receipt and an unknown id are indistinguishable, both by design: this never confirms or denies that a private receipt exists.

NameTypeReqDescription
receipt_idstringyesExact receipt id, e.g. "OCD-RCP-EMG6-6KR4-PQSG-MZPQ".

No output schema declared.

No examples provided.

inspect_allowance ~74

FREE. Deterministically inspect an ERC-20 allowance/revocation request against explicit network/token/spender/value policy. No wallet action, no signing, no chain read unless a separately requested preflight asks for it.

NameTypeReqDescription
actionobjectyes–
optionsobject––
policyobjectyes–

No output schema declared.

No examples provided.

inspect_bridge ~60

FREE. Deterministically inspect a narrow Circle CCTP V2 Base-to-Ethereum native-USDC bridge request against explicit policy. No wallet action, no signing, no chain read.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

inspect_payment ~144

FREE. Pure deterministic inspection of a proposed payment against structured policy (amount/network/asset/recipient/resource) — no external evidence, no sanctions screening, no cryptographic signing, no receipt. Returns the same ALLOW / REQUIRE_APPROVAL / BLOCK decision semantics as POST /x402/preflight-payment for the deterministic checks alone, so a caller can sanity-check a proposal before deciding whether the paid preflight (adds optional sanctions evidence and a signed, independently-verifiable receipt, $0.01) is worth paying for. This result is NOT cryptographically attested and carries no receipt — receipt is always null.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

inspect_staking ~52

FREE. Deterministically inspect a narrow Ethereum Lido stETH submit request against explicit policy. No wallet action, signing, or chain read.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

inspect_swap ~52

FREE. Deterministically inspect a narrow Base USDC-to-WETH direct Uniswap V3 swap against explicit policy. No wallet action or signing.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

observe_allowance ~62

Given a signed OCD allowance preflight artifact and submitted Base transaction hash, independently inspect its canonical-USDC Approval event, Base safe-head finality, and historical allowance state. OCD never executes the transaction.

NameTypeReqDescription
artifact–––
transaction_hashstringyes–

No output schema declared.

No examples provided.

observe_bridge ~95

Given a signed OCD bridge preflight artifact, the Base depositForBurn transaction hash, and (once available) the Ethereum receiveMessage transaction hash, independently observe both chains, verify the CCTP message identity matches, and reconcile against the authorized action. Source-only observation is reported as an evidence gap, never as completion.

NameTypeReqDescription
artifact–––
destination_transaction_hashstring––
source_transaction_hashstringyes–

No output schema declared.

No examples provided.

observe_staking ~64

Given a signed OCD staking preflight artifact and Ethereum transaction hash, independently inspect the canonical Lido Submitted event, transaction sender/value, optional minted shares, and Ethereum finalized-head finality. OCD never stakes ETH.

NameTypeReqDescription
artifact–––
transaction_hashstringyes–

No output schema declared.

No examples provided.

observe_swap ~64

Given a signed OCD swap preflight artifact and Base transaction hash, independently inspect direct Uniswap V3 exactInputSingle calldata, ERC-20 transfers, and Base safe-head finality. OCD never executes the swap.

NameTypeReqDescription
artifact–––
transaction_hashstringyes–

No output schema declared.

No examples provided.

preflight_allowance ~73

Call BEFORE an agent asks its wallet to approve or revoke a Base USDC ERC-20 allowance. OCD evaluates strict policy and returns a signed portable allowance artifact. ALLOW is policy only, never wallet authority.

NameTypeReqDescription
actionobjectyes–
optionsobject––
policyobjectyes–

No output schema declared.

No examples provided.

preflight_bridge ~71

Call BEFORE an agent asks its wallet to bridge Base USDC to Ethereum via Circle CCTP V2 (depositForBurn). OCD evaluates strict policy and returns a signed portable bridge artifact. ALLOW is policy only, never wallet authority.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

preflight_payment ~129

Call BEFORE an agent authorizes an autonomous payment. Evaluates it against your policy (max amount, allowed networks/assets, expected recipient, allowed origins) and returns a signed PREFLIGHT receipt -- ALLOW, REQUIRE_APPROVAL, or BLOCK, with reasons -- independently verifiable by anyone. Policy evaluation only: OCD never holds, moves, or authorizes funds. The wallet/x402 client separately authorizes execution after; ALLOW does not guarantee it will proceed.

NameTypeReqDescription
actionobjectyes–
optionsobject––
policyobjectyes–
referencesobject––

No output schema declared.

No examples provided.

preflight_staking ~62

Call BEFORE an agent asks its wallet to submit ETH to Lido stETH. OCD evaluates strict policy and returns a signed portable staking artifact. ALLOW is policy only, never wallet authority.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

preflight_swap ~65

Call BEFORE an agent asks its wallet to execute a narrow Base USDC-to-WETH direct Uniswap V3 swap. OCD returns a signed portable policy artifact. ALLOW is policy only, never wallet authority.

NameTypeReqDescription
actionobjectyes–
policyobjectyes–

No output schema declared.

No examples provided.

screen_name ~164

OFAC name screening: fuzzy-match a person or company name against the official US Treasury OFAC Specially Designated Nationals (SDN) list (primary names + strong aliases). Returns scored candidate matches with the matched name, SDN type, and program. SCOPE: this is a screening aid for AML / KYC / sanctions compliance — a match is a candidate to investigate with secondary identifiers (DOB, nationality, ID), NOT a determination. Weak AKAs are not screened, per OFAC guidance.

NameTypeReqDescription
namestringyesPerson or company name to screen against the OFAC SDN list
thresholdnumber–Optional match confidence cutoff 0.5–1.0 (default 0.85). Lower = more candidates, more false positives.

No output schema declared.

No examples provided.

screen_wallet ~126

Exact match of an EVM wallet address against the digital currency address identifiers on the official US Treasury OFAC SDN List (validated snapshot, refreshed hourly). Returns signed listed / not_listed, the SDN entry, dataset provenance and limits. SDN only: not EU/UN/UK lists, no ownership or 50% rule analysis; a non-match is not legal clearance. Refused before payment if current data is unavailable. Call before sending funds to an address.

NameTypeReqDescription
addressstringyesEVM wallet address (0x + 40 hex) to sanctions-screen

No output schema declared.

No examples provided.

verify_receipt ~179

Independently checks whether a receipt is cryptographically VALID, INVALID, or UNVERIFIABLE, with a reason code. Free, no payment. Pass EITHER receipt_id (looks it up first, must be public) OR a complete receipt envelope you already hold (verified directly, no publication needed). This is a convenient ONLINE check -- it trusts this server to have honestly fetched the real signing-key registry. Running the same check yourself offline (the published @onchaindiligence/agent-evidence package) is a strictly stronger trust position; this tool does not replace that option.

NameTypeReqDescription
envelope––A complete receipt envelope you already hold ({schema, receipt, proof}) to verify directly. Mutually exclusive with receipt_id.
receipt_idstring–Look up and verify a public receipt by exact id. Mutually exclusive with envelope.

No output schema declared.

No examples provided.

verify_uk_company ~112

UK company KYB lookup via the official Companies House register. Given a UK registration number, returns legal status (active/dissolved), company type, incorporation date, registered office, and people with significant control (PSC / beneficial owners). Call to confirm a UK business is real, active, and who controls it, for KYB onboarding and counterparty due diligence. Authoritative UK government data.

NameTypeReqDescription
companyNumberstringyesUK Companies House registration number to verify, e.g. 00000006

No output schema declared.

No examples provided.

verify_us_company ~133

US public company verification via SEC EDGAR. Given a ticker, CIK, or company name, returns entity name, CIK, industry (SIC), state of incorporation, exchanges/tickers, address, and latest SEC filing. Ambiguous names return candidates, never a silent selection. Covers SEC-registered PUBLIC companies and funds only -- not private US companies. Call for KYB and counterparty due diligence on listed US entities.

NameTypeReqDescription
querystringyesUS public company ticker, SEC CIK, or company name — e.g. "AAPL", "0000320193", or "Apple Inc"

No output schema declared.

No examples provided.

Install

How do I install the OnChainDiligence MCP server?

OnChainDiligence is a hosted endpoint at https://mcp.onchaindiligence.com/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 · mcp.onchaindiligence.com

# add to Claude Code
claude mcp add --transport http com-onchaindiligence-compliance 'https://mcp.onchaindiligence.com/mcp'
Common questions

What is the OnChainDiligence MCP server?

OnChainDiligence is an MCP server listed in the public MCP registry as com.onchaindiligence/compliance. Payment evidence and policy preflight, plus paid sanctions and company Evidence Provider checks. This page covers its hosted endpoint (https://mcp.onchaindiligence.com/mcp).

Is the OnChainDiligence MCP server safe to use?

OnChainDiligence scores 84 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 OnChainDiligence MCP server expose?

OnChainDiligence exposes 21 tools: screen_wallet, screen_name, verify_uk_company, verify_us_company, diligence, and 16 more. Their descriptions and schemas cost roughly 2,042 tokens of context every time the server is loaded.

Does the OnChainDiligence MCP server require authentication?

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

Is the OnChainDiligence MCP server still maintained?

OnChainDiligence is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.