Build, deploy, and govern AI inside the systems your teams already use. Zero trust security, agentic workflows, and enterprise-grade governance.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · api.squared.ai
27tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.squared.ai/mcp
Skill page: https://www.mcpbundles.com/skills/squared-mcp-df5c3b1685
Explore capabilities (27)
other 25
Showing 25 of 27
Showing 25 of 27 tools from the public preview. Connect the server to inspect the full live tool list.
Connectors9
Agentic Coding Security3
Syncs3
Tools3
Workflows3
Connector Definitions2
Other capabilities2
Workflows Run
other
workflows_run
Trigger a workflow run. Starts the workflow execution via Temporal and returns the result or an action_required status if human approval is needed.
Workflows Run — Trigger a workflow run. Starts the workflow execution via Temporal and returns the result or an action_required status if human approval is needed.
Workflows List — List all workflows in a workspace. Returns workflow id, name, description, status, trigger type, configuration, components, edges, and version metadata.
Workflows List Runs — List workflow runs for a specific workflow. Returns run status, duration, tokens used, error messages, and timing. Supports filtering by status and time period.
Tools List — List all enabled custom tools registered in a workspace. Returns tool id, name, label, description, and tool type.
Tools Call — Invoke a single action on a registered custom tool's MCP server. Always call tools_actions first to confirm the action name and its input schema before calling this.
Tools Actions — List the actions exposed by a specific custom tool's MCP server, including each action's name, description, and input schema. Call this before tools_call to discover valid action names and required arguments.
Syncs Show — Show details of a specific sync by ID. Returns sync name, status, schedule, configuration, source, destination, and model.
Syncs List — List all syncs in a workspace. Returns paginated results with sync name, status, schedule, source, destination, and model info.
Syncs List Runs — List sync runs for a specific sync. Returns run status, timing, row counts, and error information.
Reports Workspace Activity — Get workspace activity report showing sync run statistics over time. Returns sync run counts and row counts grouped by time intervals.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Build, deploy, and govern AI inside the systems your teams already use. Zero trust security, agentic workflows, and enterprise-grade governance.
How do I connect AISquared to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does AISquared provide?
Operate this server?
Request removal if you do not want AISquared listed here, or claim the listing if you want to manage it on MCPBundles.
Operate AISquared?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Models List — List all models in a workspace. Returns model name, query, query type, connector, and configuration.
Connectors Update — Update an existing connector's name, description, or configuration. The configuration is PARTIAL: only the keys you pass change, every other key keeps its stored value (nested objects such as credentials merge key by key). The tool tests the merged configuration itself before saving, so do not call connectors_test first. To change the authentication type, pass every field of the new mode. The connector type cannot be changed: delete and re-create instead. Returns JSON {status: 'updated' or 'unch
Connectors Test — Test a connector configuration before creating it, without persisting anything. Returns JSON {success, message}. The result never echoes the configuration back.
Connectors Show — Show details of a specific connector by ID. Returns a compact JSON object with the connector's id, name, description, connector_type, connector_name, its current configuration with every secret field replaced by '*************' (secrets are never returned), and dependencies: counts of the models, syncs, and workflow components that use it.
Connectors Query Source — Execute a query against a source connector and return the results. Only works with source-type connectors. Pagination is applied automatically — do NOT include LIMIT or OFFSET in the query; use the page and per_page arguments instead. Returns a JSON object {data: [...rows], page, per_page}.
Connectors List — List all connectors (sources and destinations) in a workspace. Optionally filter by type, category, or provider name. Returns a compact JSON list with each connector's id, name, description, connector_type, and connector_name.
Connectors Execute Model — Execute a payload against an AI/ML model source connector and return the results. Only works with AI/ML model source-type connectors. Returns the model response data.
Connectors Discover — Discover the catalog (schema) of a connector. Returns available streams/tables and their schemas. Use refresh=true to force re-discovery.
Connectors Delete — Delete a connector. This action is permanent and cannot be undone. With confirm=false (the default) nothing is deleted: returns JSON {status: 'preview' or 'blocked', reason, dependencies, confirm_token} listing the models, syncs, and workflow components that use the connector. Deletes only with confirm=true AND the confirm_token from that preview, which you may pass ONLY after the user answered the 'Confirm deletion' question with Delete in this conversation — never on your own initiative. Retur
Connector Definitions Spec — Get the connection specification (JSON schema of required and optional fields) for a connector type. The spec is the single source of truth for the fields needed to create a connector — never ask the user for fields that are not in it. connector_name is case-sensitive; use connector_definitions_list to find the exact name.
Connector Definitions List — List the connector types available to create (e.g. Postgresql, Bigquery, Salesforce). Use this before creating a new connector to find the exact connector_name. Returns a compact JSON list with name, title, category, and sub_category.
Connectors Create — Create a new connector in the workspace from a configuration assembled from the connector spec. Test the configuration with connectors_test first. Returns JSON {status, connector_id, name}; if the same connector already exists under this name, returns it instead of failing. A connector of a DIFFERENT type already using this name is an error — ask the user for a different display name and retry.
Agentic Coding Security Trigger Scan — Start a security scan of the app's current code. Use after applying security fixes to verify them. If a scan is already running you get that scan's id instead of an error. Poll it with agentic_coding_security_get_scan.
Agentic Coding Security List Findings — List the app's security findings with full detail (description, location, remediation, references). During a security-fix task, call this with the finding ids you were given to see exactly what to fix and where.
Agentic Coding Security Get Scan — Get a security scan's status, severity counts and coverage. Poll this after agentic_coding_security_trigger_scan until status is completed or failed, then report the result.
Showing the first 25 tools — full list and schemas: Directory API.
MCPBundles probed 27 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does AISquared require?
AISquared may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.