openagents
OpenAgents - The collaboration OS for AI agents
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
openagents-org
Source: github_code
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
AMP_HOMEASDF_DATA_DIRBUN_INSTALLChocolateyInstallComSpecDENO_INSTALLELECTRON_RENDERER_URLFNM_DIRNPM_CONFIG_PREFIXNVM_BINNVM_DIRNVM_HOMENVM_SYMLINKOA_WORKSPACE_TOKENOPENAGENTS_AGENT_NAMEOPENAGENTS_CHANNEL_NAMEOPENAGENTS_DEVTOOLS_PORTOPENAGENTS_DOWNLOAD_REGIONOPENAGENTS_ENDPOINTOPENAGENTS_INSTALL_STALL_MSOPENAGENTS_SKIP_UPDATE_CHECKOPENAGENTS_WORKSPACE_IDOPENAGENTS_WORKSPACE_TOKENOPENCODE_INSTALL_DIRPNPM_HOMEProgramFilesSCOOPSHELLSystemRootUV_TOOL_DIRVOLTA_HOMEXDG_BIN_HOMEuses uv tool install, which places aider in $ →XDG_DATA_HOME$/../bin → ~/.local/bin (and always in the uv tools venv).THREADPOOL_TOKENSBRAVE_API_KEYEXA_API_KEYMAX_BROWSER_TABSBROWSERFABRIC_API_KEYBROWSERFABRIC_URLBROWSERFABRIC_PROVISION_SECRETBROWSER_SANDBOXBROWSER_TAB_IDLE_MINUTESBROWSER_CLOSE_RETRY_WINDOW_HOURSBROWSER_CLOSING_STALE_MINUTESBROWSER_SWEEP_MAX_ACTIONSAUTH_MODEFIREBASE_PROJECT_IDFIREBASE_CREDENTIALS_JSONAPPLE_CLIENT_IDSAPNS_AUTH_KEYAPNS_AUTH_KEY_PATHAPNS_KEY_IDAPNS_TEAM_IDAPNS_BUNDLE_IDAPNS_ENVIRONMENTIDENTITY_MODEAGENT_TIMEOUT_SECONDSENFORCE_AGENT_LIFECYCLE_AUTHCORS_ORIGINSFILE_STORAGE_BACKENDFILE_STORAGE_PATHS3_BUCKETS3_REGIONMAX_FILE_SIZEAPP_ANDROID_LATEST_VERSIONAPP_ANDROID_LATEST_BUILDAPP_ANDROID_MIN_BUILDAPP_ANDROID_UPDATE_URLAPP_ANDROID_RELEASE_NOTESAPP_IOS_LATEST_VERSIONAPP_IOS_LATEST_BUILDAPP_IOS_MIN_BUILDAPP_IOS_UPDATE_URLAPP_IOS_RELEASE_NOTESROUTER_LLM_ENABLEDROUTER_LLM_PROVIDERROUTER_LLM_MODELROUTER_LLM_API_KEYROUTER_LLM_BASE_URLANTHROPIC_API_KEYe.g. AIDER_MODEL=sonnet / opus / claude-3-5-sonnet-20241022CLOUD_AGENT_MAX_CONTEXT_MESSAGESCLOUD_AGENT_MAX_CONTEXT_CHARSCLOUD_AGENT_MAX_DEPTHYUMI_ENABLEDYUMI_API_KEYYUMI_BASE_URLYUMI_MODELYUMI_MAX_TOOL_ITERATIONSGOOGLE_OAUTH_CLIENT_IDGOOGLE_OAUTH_CLIENT_SECRETFRONTEND_BASE_URLRESEND_API_KEYEMAIL_FROMINVITE_TTL_DAYSSLACK_CLIENT_IDSLACK_CLIENT_SECRETSLACK_SIGNING_SECRETCAMPAIGN_ENABLEDCAMPAIGN_GATEWAY_URLCAMPAIGN_GATEWAY_MASTER_KEYCAMPAIGN_TOTAL_CAP_USDCAMPAIGN_DAILY_GRANT_USDFEEDBACK_EMAIL_TOHOSTVERCELAWS_LAMBDA_FUNCTION_NAMEDB_PGBOUNCEROUTBOUND_ALLOWED_PORTSSOURCE_APIDRY_RUN_CHANNELOPENAI_API_KEYe.g. AIDER_MODEL=gpt-4oOPENAI_BASE_URLCODEX_MODELOPENCLAW_MODELCURSOR_MODELGOOSE_MAX_TURNSoverride ) and --max-tool-repetitions (default 12,KIMI_API_KEYMOONSHOT_API_KEYLLM_API_KEYvariable your is injected into. It accepts auto (default),KIMI_BASE_URLLLM_BASE_URLrequires LLM_BASE_URL; the model is normalized to openai/<model>KIMI_MODELLLM_MODELOPENCLAW_DIRECT_APIOPENCLAW_WORKSPACE_DIRAZURE_OPENAI_API_KEYOPENAI_API_VERSIONOPENAGENTS_API_KEYPYTHONIOENCODINGDEFAULT_LLM_PROVIDERDEFAULT_LLM_MODEL_NAMEDEFAULT_LLM_API_KEYDEFAULT_LLM_BASE_URLAWS_DEFAULT_REGIONAWS_BEARER_TOKEN_BEDROCKGOOGLE_API_KEYMINIMAX_API_KEYNEXT_PUBLIC_API_URLNEXT_PUBLIC_GA_IDNEXT_PUBLIC_POSTHOG_HOSTNEXT_PUBLIC_POSTHOG_KEYDATABASE_URLREDIS_URLPORTTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
29/29 tools missing one or more hints — workspace_get_history (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); workspace_get_agents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); workspace_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +26 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
No hardcoded API keys
2 live-looking API keys in source: 2 Google API key
Move secrets to environment variables (process.env.X) or your secret manager.
Tool test coverage
17/29 tools referenced in tests (59%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
36 calls in production code run through a shell (packages/agent-connector/src/mcp-server.js:834, packages/launcher/src/main/index.ts:2267, packages/agent-connector/src/autostart.js:59)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets not written to files
1 secret value written to files
Avoid persisting secrets to disk. Keep them in memory or your secret manager.
Secrets not logged
1 secret value sent to logger.info
Redact or omit secret values from log output.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/openagents-org/openagents)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check