composio
mcp0.11.1Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
By ComposioHQ | 191 findings | Scanned 6/15/2026 | tooltrust-scanner/v0.3.17 | 28.8k
Risk Summary
Safe With Normal ControlsDep Visibility is the main signal, but overall risk remains within an acceptable range.
Potential impact: This finding indicates the tool should be reviewed before it is trusted.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (191)
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
auth_configs.by_nanoid.updateconnected_accounts.createconnected_accounts.deleteconnected_accounts.status.updateconnected_accounts.refreshconnected_accounts.link.createorg.project.config.updateorg.owner.project.new.createorg.owner.project.getorg.owner.project.deleteorg.owner.project.regenerate_api_key.createwebhook_subscriptions.listwebhook_subscriptions.createwebhook_subscriptions.getwebhook_subscriptions.updatewebhook_subscriptions.deletewebhook_subscriptions.rotate_secret.createwebhook_subscriptions.event_types.listwebhook_endpoints.listwebhook_endpoints.self.createwebhook_endpoints.getwebhook_endpoints.createtools.enum.listtoolkits.multi.createtools.execute.createtools.execute.input.createtools.execute.proxy.createtrigger_instances.upsert.createtrigger_instances.active.listtrigger_instances.manage.updatemcp.servers.generate.createfiles.upload.request.createtool_router.session.execute.createtool_router.session.execute_meta.createtool_router.session.gettool_router.session.link.createtool_router.session.proxy_execute.createtool_router.session.search.createtool_router.session.mounts.items.listtool_router.session.mounts.download_url.createtool_router.session.mounts.upload_url.createFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
input schema exposes 12 properties (threshold: 10)
tools.listinput schema exposes 15 properties (threshold: 10)
trigger_instances.active.listinput schema exposes 11 properties (threshold: 10)
tool_router.session.createtool_router.session.updateFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
auth.session.info.listauth_configs.listauth_configs.createauth_configs.getauth_configs.by_nanoid.updateauth_configs.deleteauth_configs.updateconnected_accounts.listconnected_accounts.createconnected_accounts.getconnected_accounts.updateconnected_accounts.deleteconnected_accounts.status.updateconnected_accounts.refreshconnected_accounts.link.createorg.project.config.listorg.project.config.updateorg.owner.project.new.createorg.owner.project.list.listorg.owner.project.getorg.owner.project.deleteorg.owner.project.regenerate_api_key.createwebhook_subscriptions.listwebhook_subscriptions.createwebhook_subscriptions.getwebhook_subscriptions.updatewebhook_subscriptions.deletewebhook_subscriptions.rotate_secret.createwebhook_subscriptions.event_types.listwebhook_endpoints.listwebhook_endpoints.self.createwebhook_endpoints.getwebhook_endpoints.createwebhook_endpoints.updatetoolkits.listtoolkits.categories.listtoolkits.gettools.listtools.enum.listtools.gettoolkits.multi.createtools.execute.createtools.execute.input.createtools.execute.proxy.createtrigger_instances.upsert.createtrigger_instances.active.listtrigger_instances.manage.updatetrigger_instances.manage.deletetriggers_types.list.enum.listtriggers_types.gettriggers_types.listmcp.servers.listmcp.servers.createmcp.servers.custom.createmcp.servers.generate.createmcp.getmcp.updatemcp.deletemcp.app.getmcp.servers.instances.listmcp.servers.instances.createmcp.servers.instances.deletefiles.list.listfiles.upload.request.createtool_router.session.createtool_router.session.execute.createtool_router.session.execute_meta.createtool_router.session.gettool_router.session.updatetool_router.session.link.createtool_router.session.proxy_execute.createtool_router.session.toolkits.listtool_router.session.tools.listtool_router.session.search.createtool_router.session.mounts.items.listtool_router.session.mounts.download_url.createtool_router.session.mounts.upload_url.createtool_router.session.mounts.delete.createtoolkits.changelog.listFix: Review and remediate the identified issue.
declared capabilities: filesystem access
auth_configs.createauth_configs.updateconnected_accounts.listconnected_accounts.updatewebhook_endpoints.updatetrigger_instances.manage.deletemcp.servers.listmcp.servers.createmcp.servers.custom.createmcp.updatemcp.app.getmcp.servers.instances.listmcp.servers.instances.createmcp.servers.instances.deletefiles.list.listtool_router.session.createtool_router.session.updatetool_router.session.mounts.delete.createdeclared capabilities: filesystem access, HTTP requests
auth_configs.by_nanoid.updateorg.owner.project.new.createwebhook_subscriptions.deletewebhook_subscriptions.rotate_secret.createwebhook_endpoints.createtrigger_instances.upsert.createdeclared capabilities: filesystem access, database access
auth_configs.deletemcp.deletedeclared capabilities: network access, filesystem access
connected_accounts.createconnected_accounts.link.createorg.project.config.updateorg.owner.project.regenerate_api_key.createtoolkits.multi.createfiles.upload.request.createtool_router.session.link.createtool_router.session.mounts.items.listtool_router.session.mounts.download_url.createtool_router.session.mounts.upload_url.createdeclared capabilities: filesystem access, database access, HTTP requests
connected_accounts.deleteconnected_accounts.status.updateorg.owner.project.deletedeclared capabilities: network access, filesystem access, HTTP requests
connected_accounts.refreshwebhook_subscriptions.createwebhook_subscriptions.updatewebhook_endpoints.self.createtools.execute.proxy.createdeclared capabilities: network access, HTTP requests
org.owner.project.getdeclared capabilities: HTTP requests
webhook_subscriptions.listwebhook_subscriptions.getwebhook_subscriptions.event_types.listwebhook_endpoints.listwebhook_endpoints.gettools.enum.listtrigger_instances.active.listdeclared capabilities: database access
tools.listdeclared capabilities: code/command execution, filesystem access
tools.execute.createtools.execute.input.createtool_router.session.execute.createtool_router.session.execute_meta.createdeclared capabilities: code/command execution, filesystem access, HTTP requests
trigger_instances.manage.updatedeclared capabilities: network access, filesystem access, database access
mcp.servers.generate.createtool_router.session.search.createdeclared capabilities: network access
tool_router.session.getdeclared capabilities: code/command execution, network access, filesystem access, database access, HTTP requests
tool_router.session.proxy_execute.createFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
input parameter "validate_credentials" accepts a credential (informational; not evidence of insecure handling)
connected_accounts.createconnected_accounts.refreshinput parameter "require_mcp_api_key" accepts a credential (informational; not evidence of insecure handling)
org.project.config.updateinput parameter "mask_secret_keys_in_connected_account" accepts a credential (informational; not evidence of insecure handling)
org.project.config.updateinput parameter "should_create_api_key" accepts a credential (informational; not evidence of insecure handling)
org.owner.project.new.createFix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y composio"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)