mcp-atlassian@0.24.7
VERIFIED· not startedPublisher claims: "The Model Context Protocol (MCP) Atlassian integration is an open-source implementation that bridges Atlassian products (Jira and Confluence) with AI language models following Anthropic's MCP specification. This project enables secure, contextual AI interactions with Atlassian tools while maintaining data privacy and security. Key features include:" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: Verified 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
ATLASSIAN_OAUTH_ACCESS_TOKENATLASSIAN_OAUTH_ALLOWED_CLIENT_REDIRECT_URISATLASSIAN_OAUTH_ALLOWED_GRANT_TYPESATLASSIAN_OAUTH_CLIENT_IDATLASSIAN_OAUTH_CLIENT_SECRETATLASSIAN_OAUTH_CLOUD_IDATLASSIAN_OAUTH_ENABLEATLASSIAN_OAUTH_INSTANCE_URLATLASSIAN_OAUTH_REDIRECT_URIATLASSIAN_OAUTH_SCOPECONFLUENCE_API_TOKENCONFLUENCE_CLIENT_KEY_PASSWORDCONFLUENCE_OAUTH_CLIENT_IDCONFLUENCE_OAUTH_CLIENT_SECRETCONFLUENCE_PERSONAL_TOKENJIRA_API_TOKENJIRA_CLIENT_KEY_PASSWORDJIRA_OAUTH_CLIENT_IDJIRA_OAUTH_CLIENT_SECRETJIRA_PERSONAL_TOKENor--oauth-setup/--client-secret/--confluence-token/--confluence-personal-token/--jira-token/--jira-personal-token/--oauth-client-secret/--oauth-access-token/--oauth-client-id/--oauth-redirect-uriConfiguration, not credentials: ATLASSIAN_PROXY_WPAD_URL, CONFLUENCE_ATTACHMENT_DOWNLOAD_USE_V1, CONFLUENCE_CLIENT_CERT, CONFLUENCE_CLIENT_KEY, CONFLUENCE_SPACES_FILTER, CONFLUENCE_SSL_VERIFY, CONFLUENCE_TIMEOUT, CONFLUENCE_URL, CONFLUENCE_USERNAME, CURL_CA_BUNDLE, DISABLE_JIRA_MARKUP_TRANSLATION, ENABLED_TOOLS, HIERARCHY_LINK_PHRASES, JIRA_CLIENT_CERT, JIRA_CLIENT_KEY, JIRA_INTERNAL_ONLY_PROJECTS, JIRA_PROJECTS_FILTER, JIRA_SLA_METRICS, JIRA_SLA_TIMEZONE, JIRA_SLA_WORKING_DAYS- Where it talks to
- atlassian.com, atlassian.net (its own)Also your-company.com, chatgpt.com, other.example — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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, and read the third-party hosts first. The code names your-company.com, chatgpt.com, other.example as well as its own vendor. The guard injects ATLASSIAN_OAUTH_ACCESS_TOKEN, ATLASSIAN_OAUTH_ALLOWED_CLIENT_REDIRECT_URIS, ATLASSIAN_OAUTH_ALLOWED_GRANT_TYPES, ATLASSIAN_OAUTH_CLIENT_ID, ATLASSIAN_OAUTH_CLIENT_SECRET, ATLASSIAN_OAUTH_CLOUD_ID, ATLASSIAN_OAUTH_ENABLE, ATLASSIAN_OAUTH_INSTANCE_URL, ATLASSIAN_OAUTH_REDIRECT_URI, ATLASSIAN_OAUTH_SCOPE, CONFLUENCE_API_TOKEN, CONFLUENCE_CLIENT_KEY_PASSWORD, CONFLUENCE_OAUTH_CLIENT_ID, CONFLUENCE_OAUTH_CLIENT_SECRET, CONFLUENCE_PERSONAL_TOKEN, JIRA_API_TOKEN, JIRA_CLIENT_KEY_PASSWORD, JIRA_OAUTH_CLIENT_ID, JIRA_OAUTH_CLIENT_SECRET, JIRA_PERSONAL_TOKEN only into requests to atlassian.com (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.23.1
vet-skills diff mcp-atlassian 0.23.1 0.24.7This version reaches for something 0.23.1 did not: 1 new host (other.example). Compared from the two recorded runs, not from source.
- New hosts
- other.example
0.23.1 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 2026-11-20 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
# Disable trust_env for PAT and OAuth to prevent .netrc from overridingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# explicit credentials (#860). Basic auth can safely use .netrc.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# PAT and OAuth sessions run with trust_env=False (so .netrc cannotFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.attacks (e.g., ``../../etc/passwd``).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.if [ ! -f ".env" ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .env import is_env_truthyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."--env-file", type=click.Path(exists=True, dir_okay=False), help="Path to .env file"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.source .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .env import get_int_envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .env import (Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."environment variable or in the default .env file (--env-file "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.auth_paths = frozenset({self.mcp_server_ref.get_streamable_http_path()})Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.echo " 1. Start DC instances: cd tests/e2e/docker && docker compose --env-file .env.example up -d"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."Attempting to load environment from default .env file if it exists"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.map(ord, "") # ZWSP, ZWNJ, ZWJ, word-joiner, BOMFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# set in the environment (or .env) before the server starts.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Check if .env file existsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Read from .env via dotenv_values() since load_dotenv() hasn't run yet.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Disable trust_env for PAT and OAuth to prevent .netrc from overridingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""Swallow SIGPIPE so a closed pipe cannot kill the process."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# explicit credentials (#860). Basic auth can safely use .netrc.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.echo "Note: .env file not found. Using defaults for DC instances (localhost:8080/8090)."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.from .env import is_env_truthyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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.