Credal is a unified platform that lets enterprises build, govern, and deploy AI agents and Managed Compute Platform (MCP) servers without code. It enforces fine‑grained, role‑based and tool‑level access controls, automatic permission inheritance from SSO, and human‑in‑the‑loop approval gates, while providing full audit logs and real‑time risk monitoring for actions across systems like Salesforce, Jira, Slack, and Google Workspace.
Funding
$5M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CNFounders
Product
Problem
Enterprises struggle to deploy AI agents that can safely access and act on data across multiple internal systems while maintaining strict governance, auditability, and compliance with security policies. Without centralized controls, AI-driven workflows risk data leakage, unauthorized actions, and lack of visibility for administrators.
Solution
Credal provides a unified platform for building, governing, and deploying enterprise AI agents and Managed Compute Platform (MCP) servers. The no‑code builder lets teams create agents that reason over company data and execute actions in systems such as Salesforce, Jira, Slack, Google Workspace, and dozens of other tools. Permissions are automatically inherited from existing SSO and data sources, ensuring agents only see what the invoking user can access. Fine‑grained role‑based and tool‑level controls, human‑in‑the‑loop approval gates, and configurable policies enforce security and compliance across all agent actions. Every prompt, response, and tool invocation is logged with full traceability, enabling real‑time risk monitoring and comprehensive audit trails. The platform supports both managed frontier models (e.g., GPT‑4o, Claude, Gemini) and bring‑your‑own LLM deployments, with options for cloud, single‑tenant, or on‑premise hosting.
Target Audience
Primary customers are enterprise IT, security, and operations teams—such as sales operations, engineering, marketing, and compliance groups—that need to automate workflows across multiple internal systems while maintaining strict governance and auditability.
Features
- No‑code agent builder with drag‑and‑drop workflow design and developer APIs
- Automatic permission inheritance from SSO (SAML/SCIM, Okta) and data sources (Google Drive, SharePoint, Confluence, etc.)
- Role‑based access control scoped to teams, user groups, and individual agents
- Human‑in‑the‑loop approval gates configurable per action for sensitive operations
- Pre‑built integrations with 50+ enterprise tools and ability to package custom actions in governed MCP servers
- Full audit logging of prompts, responses, and tool invocations with real‑time risk flagging
- Model‑agnostic architecture supporting managed LLMs or customer‑provided models, including Azure OpenAI and self‑hosted options
- Deployment flexibility: multi‑tenant SaaS, single‑tenant cloud, or on‑premises with SOC 2 Type II, HIPAA, and GDPR compliance