Forensics Mcp

dev.onchainforensicsPublished by onchainforensics.devv1.1.1Updated Nov 7, 2026

Token due-diligence for AI agents: grade verdicts, mint activity, settlement safety.

VerifiedSTDIODesktop onlyFinanceSecurity & Monitoring

Overview

AI-generated overview

Local MCP server that gives an assistant token due-diligence verdicts, mint activity, settlement-safety checks and token or wallet profiles from live chain…

What you can do
  • Grade a token A-F with a verdict tier, activity score and one-line comment
  • Inspect mint events, minted amounts, mint authority and the exact time window
  • Check settlement safety: registry canonicality, ERC-20 readability and pause state
  • Pull full token profiles (supply, decimals, holders, top wallets) and wallet profiles
  • List the server's other capabilities and their prices
When to use it
Useful when an agent needs a quick, rule-based judgement on whether a token is worth touching, or wants to check minting and settlement risk before interacting with a token or wallet. Grades come from deterministic rules over live chain reads, so results are repeatable.
Requirements
Runs locally via npx from the npm package onchain-forensics-mcp; no install step and no declared authentication. Network access to the onchainforensics API is needed. Optional environment variables: FORENSICS_DEV_KEY for a free developer key, plus FORENSICS_BASE_URL, FORENSICS_CHAIN (default base) and FORENSICS_TIMEOUT_MS.
Before you install
Tools are free-trial first, then paid per call in USDC via an x402 payment challenge; an agent able to sign payments may spend money, and prepaid credit packs are also offered. A developer key is requested by email and shown once. Queries go to a third-party API. Grades are heuristic verdicts, not investment advice.

Installation

In SourceWeft

  1. Open Forensics Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

On-chain Forensics MCP server

Token due-diligence tools for any MCP-capable agent: ask "should I touch this token" and get a letter grade with a reason instead of a price chart. Zero dependencies, stdio transport, no install step.

bash
npx -y onchain-forensics-mcp

Published on npm as onchain-forensics-mcp. If the registry is unreachable, the same code installs straight from GitHub: npx -y github:leohoudinisanders-byte/forensics-mcp.

Tools

ToolQuestion it answersPrice
token_verdictShould I touch this token? Grade A-F, verdict tier, activity score, one-line roast.free trial, then $0.001
token_mintsIs this token being printed? Mint events, minted amount, mint authority, exact window.free trial, then $0.02
settlesafe_checkCan this token actually settle? Registry canonicality, ERC-20 readability, pause state.free trial, then $0.02
token_profileFull readable profile: supply, decimals, holders, top wallets.free trial, then $0.05
wallet_profileIs this wallet real, and what does it hold?free trial, then $0.05
forensics_catalogWhat else can this server answer, and what does it cost? Free, no network call.free

Grades are computed by deterministic rules over live chain reads. No LLM sits in the decision path, so the same token grades the same way twice.

Install

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):

json
{  "mcpServers": {    "onchain-forensics": {      "command": "npx",      "args": ["-y", "onchain-forensics-mcp"]    }  }}

Claude Code:

bash
claude mcp add onchain-forensics -- npx -y onchain-forensics-mcp

Cursor (.cursor/mcp.json) and any other client use the same command + args pair.

LangChain / Vercel AI SDK / custom runtimes: the server speaks newline-delimited JSON-RPC 2.0 on stdio, so it drops into any MCP client implementation. Methods implemented: initialize, tools/list, tools/call, ping.

Free developer key (10,000 calls/month)

bash
curl -X POST https://api.onchainforensics.dev/functions/devKeys \  -H "Content-Type: application/json" -d '{"email":"[email protected]"}'

The response contains a key shown once. Set it and every tool call becomes a plain data read with no payment signature:

json
{  "mcpServers": {    "onchain-forensics": {      "command": "npx",      "args": ["-y", "onchain-forensics-mcp"],      "env": { "FORENSICS_DEV_KEY": "fxk_..." }    }  }}

Payment

Every tool calls the free trial tier first. When that route's daily allowance is spent, the paid endpoint answers HTTP 402 and the tool returns the decoded x402 challenge (price, USDC asset, payTo, network) rather than an error, so an agent that can sign a payment proceeds and an agent that cannot still learns the exact cost.

  • Pay per call: any x402 client against https://api.onchainforensics.dev/functions/<route>
  • Prepaid keys (no signature per call): POST /functions/forensicsCredits {"plan":"pack1"}

Env

VariableDefault
FORENSICS_BASE_URLhttps://api.onchainforensics.dev/functions
FORENSICS_CHAINbase
FORENSICS_TIMEOUT_MS45000
FORENSICS_DEV_KEYempty (falls back to free trial, then the x402 challenge)

License

MIT

Source: README.md at commit 0955bb6

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.1.1LatestNov 7, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.