Skills/PyPI/redmine-mcp-server

redmine-mcp-server@2.22.0

CAUTION· not started

Publisher claims: "MCP server that lets AI assistants manage Redmine issues, projects, wikis, and time tracking" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher jztan · publishing for 418 daysInstalls 2,264Last detonated 1 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
REDMINE_API_KEYREDMINE_API_KEY_LOGIN_BINDING_CRYPTOREDMINE_AUTH_MODEREDMINE_MCP_ACCESS_TOKEN_EXPIRY_SECONDSREDMINE_OAUTH_CLIENT_IDREDMINE_OAUTH_DISCOVERY_ASREDMINE_PASSWORDConfiguration, not credentials: ATTACHMENT_EXPIRES_MINUTES, ATTACHMENTS_DIR, AUTO_CLEANUP_ENABLED, CLEANUP_INTERVAL_MINUTES, FASTMCP_HOME, FASTMCP_STREAMABLE_HTTP_PATH, PUBLIC_HOST, PUBLIC_PORT, PUBLIC_SCHEME, REDMINE_CRM_EDITION, REDMINE_INTROSPECT_CLIENT_ID, REDMINE_MCP_ALLOW_TOOLS, REDMINE_MCP_ALLOW_TOOLS_FILE, REDMINE_MCP_ALLOWED_CLIENT_REDIRECT_URIS, REDMINE_MCP_BASE_URL, REDMINE_MCP_CONTENT_BASE64_MAX_BYTES, REDMINE_MCP_EXTENSIONS, REDMINE_MCP_JOURNAL_VALUE_MAX_CHARS, REDMINE_MCP_SCOPES, REDMINE_MCP_TRANSPORT, REDMINE_MCP_UPLOAD_FILE_ROOTS, REDMINE_MCP_UPLOAD_MAX_BYTES, REDMINE_MCP_UPLOAD_TICKET_MINUTES, REDMINE_PUBLIC_URL, REDMINE_REQUIRED_CUSTOM_FIELD_DEFAULTS, REDMINE_SSL_CERT, REDMINE_SSL_CLIENT_CERT, REDMINE_SSL_VERIFY, REDMINE_TEXT_FORMATTING, REDMINE_URL, REDMINE_USERNAME, SERVER_HOST, SERVER_PORT
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for REDMINE_API_KEY, REDMINE_API_KEY_LOGIN_BINDING_CRYPTO, REDMINE_AUTH_MODE, REDMINE_MCP_ACCESS_TOKEN_EXPIRY_SECONDS, REDMINE_OAUTH_CLIENT_ID, REDMINE_OAUTH_DISCOVERY_AS, REDMINE_PASSWORD and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- uvx redmine-mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 2.21.0

vet-skills diff redmine-mcp-server 2.21.0 2.22.0

In the sandbox, this version reached for nothing 2.21.0 did not. Compared from the two recorded runs, not from source.

2.21.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-15 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Collapsed <details> block carrying instructions; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:291 · Collapsed <details> block carrying instructions<summary><strong>OAuth2 mode</strong> (multi-user, Redmine 6.1+)</summary> Each MCP request carries its own `Authorization: Bearer <token>`, so every user autheFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:310 · Collapsed <details> block carrying instructions<summary><strong>OAuthProxy mode</strong> (hosted deployments with client self-registration)</summary> FastMCP acts as the MCP-facing authorization server: it hFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/tools/files.py:554 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# name like "../../etc/passwd" comes back as "passwd". TheFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/redmine_mcp_server/_oauth_proxy.py:100 · Credential pass-through configuration — agent relays sensitive credentials"proxy tokens and derive encrypted storage."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Destructive file system command detectedDockerfile:45 · Destructive file system command detectedrm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
URL with embedded credentialssrc/redmine_mcp_server/_ssrf.py:230 · URL with embedded credentials — may be phishing or credential leaking# Embedded credentials (http://user:pass@host) would leak to anyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_ssrf.py:136 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Strips any directory components (defeats `../../etc/passwd` andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:330 · Collapsed <details> block carrying instructions<summary><strong>api-key-login mode</strong> (per-user identity without OAuth: Easy Redmine, Redmine older than 6.1)</summary> The server acts as its own OAuth Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Collapsed <details> block carrying instructionspages/index.html:1250 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>Which Redmine versions are supported?</summary> <div class="qa-body"> <p>The integration suite passes in full against Redmine 6.1 and 7.0. Older versioFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionsrc/redmine_mcp_server/_caller.py:18 · File type combined with upload action — agent may exfiltrate local data files``GET /users/current.json`` (see :func:`resolve_staged_upload_owner`).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_client.py:283 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Please create a .env file in your working directory with REDMINE_URL defined."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:883 · Python subprocess execution detectedsubprocess.run([*shlex.split(editor), str(path)], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/redmine_mcp_server/tools/documents.py:13 · File type combined with upload action — agent may exfiltrate local data files- ``POST /uploads.json`` — upload binary, returns token (core endpoint)Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Collapsed <details> block carrying instructionspages/index.html:1298 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>What does it cost?</summary> <div class="qa-body"> <p>Nothing. It is MIT licensed, published on PyPI and GHCR, and listed in the official MCP Registry.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
HTML comment carrying imperative instructions to the agentpages/index.html:15 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileLoaded non-blocking (print→all swap) so first paint never waits on the cross-origin CSS; the fallback stacks render immediately and Geist swaps in.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageCHANGELOG.md:1024 · Authorization escalation language · informational: not an instruction fileoutside Developer Mode or an elevated shell, so the test failed in itsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:394 · Collapsed <details> block carrying instructions<summary><strong>Visual Studio Code (Native MCP Support)</strong></summary> VS Code has built-in MCP support via GitHub Copilot (requires VS Code 1.102+). **UsiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
URL with embedded credentialssrc/redmine_mcp_server/_errors.py:38 · URL with embedded credentials — may be phishing or credential leaking# HTTP basic auth embedded in URL: https://user:pass@hostFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Access to sensitive file pathstests/conftest.py:32 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# at a running Redmine. _client loads ``.env`` at import via load_dotenv() andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_upload_store.py:137 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessends ``../../etc/passwd`` hears back the ``passwd`` that Redmine willFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:73 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/conftest.py:18 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesneeds the developer's real ``.env`` config, so we leave it alone.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:433 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Access to sensitive file pathsdeploy.sh:27 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif [ ! -f .env.docker ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/main.py:291 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# tool module imports _client, which loads .env).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy.sh:28 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "❌ .env.docker file not found"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_client.py:54 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileslogger.info(f"Loaded .env from: {_env_path}")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy.sh:29 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "📋 Creating .env.docker from .env.docker.example..."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandDockerfile:63 · File permission modification command — agent changes file ownership/permissionschown -R appuser:appuser /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/conftest.py:31 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# A developer's local ``.env`` can define REDMINE_URL + credentials that pointFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Prompt injectionCHANGELOG.md:1024 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileoutside Developer Mode or an elevated shell, so the test failed in itsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Collapsed <details> block carrying instructionspages/index.html:1282 · Collapsed <details> block carrying instructions · informational: not an instruction file<summary>How does it handle a whole team rather than one user?</summary> <div class="qa-body"> <p>Several ways. A single shared API key is the simple default. OFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/main.py:426 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Note: .env is already loaded during _client importFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdeploy.sh:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Function to check if .env.docker file existsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_client.py:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPath(__file__).parent.parent.parent / ".env", # Package directory (fallback)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/redmine_mcp_server/tools/documents.py:14 · File type combined with upload action — agent may exfiltrate local data files- ``POST /projects/{id}/dmsf/commit.json`` — finalize upload as a DMSFFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionsrc/redmine_mcp_server/tools/deals.py:46 · File type combined with upload action — agent may exfiltrate local data files# POST /deals.json and PUT /deals/<id>.json actually accept. AnythingFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_client.py:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Load environment variables from .env file before reading Redmine config.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/redmine_mcp_server/_client.py:46 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesPath.cwd() / ".env", # User's current working directory (highest priority)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:245 · Python subprocess execution detectedlogin_result = subprocess.run(["gh", "auth", "login"], check=False)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/release.py:795 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionsrc/redmine_mcp_server/tools/files.py:102 · File type combined with upload action — agent may exfiltrate local data filesname == "metadata.json" or name.endswith(".tmp") or name.startswith("upload_")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈63 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jztan: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jztanPropose a patch to the maintainer