freee-mcp
Flagged as possibly malicious Reviewed: expected behaviour
Bawwab's static rules matched a pattern it treats as critical. Read the review notes: a reviewed false alarm is marked as such.
Why it was flagged
The static rules marked this “Flagged as possibly malicious” because of:
exfil.combo: Reads credentials and makes network calls (critical, 2× · first at bin/freee-mcp.js:33)
- Kind
- MCP server
- Source
- npm
- Version
0.38.3- Popularity
- 15,828 npm downloads/week (2026-11-20)
- Link
- https://www.npmjs.com/package/freee-mcp/v/0.38.3
- Scanned
- 2026-11-20T22:35:28+00:00
- Scan time
- 3.9 s
Review note: OAuth sign-in to freee and freee Sign with tokens kept in ~/.config/freee-mcp, which is the server's purpose.
Findings (4)
credential-access: Touches credentials or secrets high
bin/freee-mcp.js:33
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
`),{accessToken:c.access_token,refreshToken:c.refresh_token}}finally{o.removeCliAuthHandler(r)}}import Ue from"prompts";import{existsSync as vn}from"node:fs";import Le from"node:fs/promises";import ue
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Expected for what this tool does
freee-mcp signs in to freee with OAuth through a local 127.0.0.1 callback and saves the tokens in ~/.config/freee-mcp/tokens.json. It then calls api.freee.co.jp. 'configure' also adds its own entry to the Claude config. All of this is the stated purpose.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls critical
bin/freee-mcp.js:33
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
`),{accessToken:c.access_token,refreshToken:c.refresh_token}}finally{o.removeCliAuthHandler(r)}}import Ue from"prompts";import{existsSync as vn}from"node:fs";import Le from"node:fs/promises";import ue
What this means: Credential access together with outbound requests in one file is the shape of data theft.
The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)
Expected for what this tool does
freee-mcp signs in to freee with OAuth through a local 127.0.0.1 callback and saves the tokens in ~/.config/freee-mcp/tokens.json. It then calls api.freee.co.jp. 'configure' also adds its own entry to the Claude config. All of this is the stated purpose.
Reviewed by Claude (AI-assisted review), 2026-11-21
credential-access: Touches credentials or secrets high
bin/freee-sign-mcp.js:12
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI03 Identity and Privilege AbuseOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0083 Credentials from AI Agent Configuration
`+" (freee-mcp configure を実行して再設定)")}return this.port=r,new Promise((n,o)=>{this.server=Cr.createServer((s,i)=>{let a=new Rr(s.url,`http://127.0.0.1:${r}`);if(console.error(`Callback request: ${s.
What this means: Reads files or environment holding keys, tokens or sessions.
The rule's general advice: Confirm the tool needs this; otherwise do not install. (see the review note for this case)
Expected for what this tool does
The same OAuth flow for freee Sign (ninja-sign.com, or FREEE_SIGN_API_URL), with a local callback server and tokens saved in ~/.config/freee-mcp/sign-tokens.json. Expected for this tool.
Reviewed by Claude (AI-assisted review), 2026-11-21
exfil.combo: Reads credentials and makes network calls critical
bin/freee-sign-mcp.js:12
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesMITRE ATLAS AML.T0037 Data from Local SystemMITRE ATLAS AML.T0055 Unsecured CredentialsMITRE ATLAS AML.T0025 Exfiltration via Cyber Means
`+" (freee-mcp configure を実行して再設定)")}return this.port=r,new Promise((n,o)=>{this.server=Cr.createServer((s,i)=>{let a=new Rr(s.url,`http://127.0.0.1:${r}`);if(console.error(`Callback request: ${s.
What this means: Credential access together with outbound requests in one file is the shape of data theft.
The rule's general advice: Do not install unless the flow is understood and benign. (see the review note for this case)
Expected for what this tool does
The same OAuth flow for freee Sign (ninja-sign.com, or FREEE_SIGN_API_URL), with a local callback server and tokens saved in ~/.config/freee-mcp/sign-tokens.json. Expected for this tool.
Reviewed by Claude (AI-assisted review), 2026-11-21
1 low-severity notes (informational, do not affect the result)
install-script: Runs code at install time low
package.json:14
OWASP LLM LLM03 Supply ChainOWASP Agentic ASI04 Agentic Supply Chain VulnerabilitiesOWASP Agentic ASI05 Unexpected Code Execution (RCE)MITRE ATLAS AML.T0010.001 Supply Chain Compromise: SoftwareMITRE ATLAS AML.T0011.001 User Execution: Malicious Package
bun run build
What this means: Install hooks run automatically with your privileges before you can review anything.
What you can do: Read the script; prefer packages with no install hooks.
Dispute this result
Maintainer and think this is wrong? Open a dispute on GitHub with the target id mcp-npm-freee-mcp-06fc60.