Cequence Security has announced the general availability of Agent Personas within its AI Gateway, aiming to enhance API security by providing enterprises with detailed control over AI agent actions. This new feature offers infrastructure-level control over AI agents, addressing the crucial privilege issues that identity verification alone cannot solve.
The need for Agent Personas arises as businesses deploy AI agents through the Model Context Protocol (MCP) to connect with enterprise applications. Traditionally, verifying an agent's identity was seen as sufficient security; however, this does not adequately manage what an agent can perform. Unlike human users, AI agents lack the discernment to know when to refrain from using their granted access. Agent Personas resolve this by defining a virtual MCP endpoint correlated to each agent role using a plain-English job description.
Virtual MCP Endpoint and Single Attributable Credential
Agent Personas utilize a scoped virtual MCP endpoint for precise role-based access. For instance, a customer service AI agent might have CRM read-only privileges without modification rights, while a coding agent can access GitHub issues and create Jira tickets but lacks permission to merge pull requests. These endpoints ensure each agent's access is limited to specific responsibilities, thus minimizing lateral access risks.
Agent Personas utilize a scoped virtual MCP endpoint for precise role-based access
The release also introduces Agent Access Keys—a composite credential specifically designed for headless agents functioning in automated environments. These keys consolidate agent and user identities with persona-based privileges into a single, traceable credential, thereby offering security teams forensic precision concerning the actions taken by AI agents.
Features of Agent Personas
Key capabilities of Agent Personas include:
- Scoped virtual MCP endpoints: Define access rights for each agent role down to specific API endpoints and permission levels.
- Natural language persona creation: Specify agent tasks in plain language, and the Gateway automatically selects suitable tools.
- Single source of truth: Update a persona once for universal, immediate application across all related agents without code changes.
- Agent Access Keys: Bind agent and user identity with persona privileges into a single credential for streamlined forensic tracing.
- Per-tool policy enforcement: Implement rate limits, data masking, and approval workflows at individual tool call levels.
- Full audit trail: Attribute every tool call to its specific agent, user, persona, and timestamps.
- Model-agnostic enforcement: Apply security measures uniformly across OpenAI, Google, Anthropic, and other models.
Importance of Agent Security
The importance of securing AI agents is underscored by Gartner, noting that the primary risk is not an AI's statements but its actions. More than 80% of Fortune 500 companies have active AI agents, yet only 47% incorporate AI-specific security measures. The introduction of Agent Personas aims to facilitate the safe transition of agents from pilot to production phases.
Illustrating this, a prominent U.S. telecommunications firm has utilized Agent Personas to manage agent access in complex systems such as GitLab, Confluence, Jira, and Slack. By employing scoped virtual endpoints, the company effectively restricted agent access to necessary infrastructure, mitigating lateral access challenges.
Enterprise Adoption and Impact
"Enterprises have made massive investments in AI, and the race to put agents into production across customer experiences, employee workflows, and business operations is accelerating fast," commented Ameya Talwalkar, CEO and Co-Founder at Cequence. He highlighted the significance of security and governance, noting that Cequence's solutions help balance security needs with operational scalability.
CTO and Co-Founder Shreyans Mehta added, "AI agents have rapidly emerged as a significant channel like the web or mobile, impacting commerce, productivity, and operations. Agent Personas provides enterprises the control plane needed for secure, scalable AI access to applications and data."
Agent Personas builds upon the momentum of Cequence AI Gateway, supporting over 140 enterprise application integrations and safeguarding over 10 billion daily API interactions. Cequence is noted for its contributions to AI security through initiatives like the co-authorship of CIS Critical Security Controls® Companion Guides.
Cequence Security, the pioneer in application, API, and Agentic AI protection, announces the general availability of Agent Personas in Cequence AI Gateway. Agent Personas give enterprises granular, infrastructure-level control over what AI agents are permitted to do — down to the specific tool call — closing the critical privilege gap that identity alone cannot address.
As organizations deploy AI agents to connect to enterprise applications via the Model Context Protocol (MCP), a dangerous assumption has taken hold: that authenticating who an agent is amounts to controlling what it can do. It does not.
Virtual MCP endpoint
Agents inherit the privileges of their users and, unlike humans, have no judgement about when not to use available access. Agent Personas solves this by using a plain-English job description to define a scoped virtual MCP endpoint for each agent role.
For example, a customer service AI agent gets CRM read-only access, not the ability to modify records. A coding agent can read GitHub issues and create Jira tickets but cannot merge pull requests. A CI/CD automation agent gets access to specific pipeline tools and a single notification channel, and nothing else.
Single attributable credential
The release also introduces Agent Access Keys, a new composite credential type purpose-built for headless agents running in automated workflows. Each key binds agent identity, user identity, and persona-level privileges into a single attributable credential, giving security teams the forensic clarity to answer exactly who did what, when, and under which permissions.
Agent Personas capabilities include:
- Scoped virtual MCP endpoint per agent role: each persona defines access down to the specific API endpoint and permission level, presented as a single endpoint
- Natural language persona creation: describe in plain language what an agent should do; the gateway selects the right tools automatically
- Single source of truth: update a persona once and the change applies immediately across every agent using it, with no code changes required
- Agent Access Keys: a composite credential binding agent identity, user identity, and persona privileges into a single attributable credential for headless agents
- Per-tool policy enforcement: rate limits, data masking, and approval workflows applied at the individual tool call level
- Full audit trail: every tool call is attributable to the specific agent, user, persona, and timestamp
- Model-agnostic: enforced at the infrastructure layer across OpenAI, Google, Anthropic, open-source, and custom models equally
Complexity of securing agents
The urgency is significant. According to Gartner®, “While the current market focus is on model runtime and inference security, this approach fails to address the complexity of securing agents, where the primary risk is not what the AI says, but what the AI does.” It further states, “If an AI agent cannot prove who it is acting for and why, it should not get access to tools and data.”
More than 80% of Fortune 500 companies now deploy active AI agents, yet only 47% have AI-specific safeguards in place. Enterprises have made substantial investments in AI platforms but have struggled to move agents from pilot to production safely. Agent Personas is built to change that.
Substantial investments in AI platforms
Early deployments show how Agent Personas govern AI agent access in complex environments. One major U.S. telecommunications provider used the technology to prevent agents from crossing boundaries in tools like GitLab, Confluence, Jira, and Slack. Scoped virtual endpoints ensured each agent accessed only what it needed, eliminating lateral access risks without extra infrastructure.
“Enterprises have made massive investments in AI, and the race to put agents into production across customer experiences, employee workflows, and business operations is accelerating fast,” said Ameya Talwalkar, CEO and Co-Founder at Cequence. “However, security, governance, and scale requirements can’t be ignored. Cequence closes the gap that has been holding organizations back by automatically limiting agent tool access which lowers costs, enhances performance, and improves security.”
Powering customer commerce
“AI agents have quickly become a channel as significant as the web or mobile, powering customer commerce, employee productivity, and autonomous operations all at once,” said Shreyans Mehta, CTO and Co-Founder at Cequence.
“Agent Personas is how you govern infrastructure access at the agent level, enforcing exactly what each agent can do down to the specific API endpoint, across any model or platform. It is the control plane enterprises need to confidently and securely enable agentic AI access to applications and data.”
Agent Personas builds on strong momentum for Cequence AI Gateway, which has grown to more than 140 verified enterprise application integrations. Cequence protects more than 10 billion daily API interactions and four billion user accounts across its platform — recognized as No. 128 on the 2025 Deloitte Technology Fast 500, a Leader in the 2025 KuppingerCole Leadership Compass for API Security and Management, co-chair of TM Forum's AI-Native Blueprint Initiative on Agentic Interaction Security, and co-author of three CIS Critical Security Controls® Companion Guides for securing AI agents, LLMs, and MCP environments alongside the Centre for Internet Security and Astrix Security.
