Record · corpus.blog/posts/01a07df2-392b-7397-89dc-05139dd53045

Authorizing MCP tool calls at the gateway or inside the proxy, and what each one stops

Cerbos Blog · published 15 August 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at cerbos.dev Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
Links from this post: 24
Words captured: 2,011

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://openid.net/specs/authorization-api-1_0.html

openid.net

https://www.cerbos.dev/features-benefits-and-use-cases/dynamic-authorization-for-MCP-servers

cerbos.dev

https://openid.github.io/authzen/authzen-coaz-framework-1_0.html

openid.github.io

https://openid.github.io/authzen/authzen-coaz-mcp-binding-1_0.html

openid.github.io

https://agentgateway.dev

agentgateway.dev

https://docs.cerbos.dev/synapse/latest/extensions/envoy-extension.html

docs.cerbos.dev

https://www.cerbos.dev/ecosystem/cerbos-envoy

cerbos.dev

https://www.coalitionforsecureai.org/wp-content/uploads/2026/04/agentic-identity-and-access-control.pdf

coalitionforsecureai.org

Why audit logs are important Read at the source ↗

cerbos.dev

https://owasp.org/www-project-artificial-intelligence-security-verification-standard-aisvs-docs/

owasp.org

https://docs.cerbos.dev/cerbos/latest/policies/resource_policies.html

docs.cerbos.dev

https://docs.cerbos.dev/cerbos/latest/policies/derived_roles.html

docs.cerbos.dev

NHI security: How to manage non-human identities and AI agents Read at the source ↗

cerbos.dev

Why external authorization is essential for modern software architecture Read at the source ↗

cerbos.dev

https://www.cerbos.dev/product-cerbos-synapse

cerbos.dev

MCP authorization: Securing Model Context Protocol servers with fine-grained access control Read at the source ↗

cerbos.dev

The kill switch that never got pressed: what the OpenAI–Hugging Face incident tells us about agent authorization Read at the source ↗

cerbos.dev

https://www.cerbos.dev/features-benefits-and-use-cases/agentic-authorization

cerbos.dev

Governing AI coding agents with Cerbos Synapse Read at the source ↗

cerbos.dev

Fine-grained authorization for AI agents with Cerbos and Aperture by Tailscale Read at the source ↗

cerbos.dev

https://hub.cerbos.cloud

hub.cerbos.cloud

https://www.cerbos.dev/workshop

cerbos.dev

https://solutions.cerbos.dev/zero-trust-for-ai-securing-mcp-servers

solutions.cerbos.dev

https://www.cerbos.dev/blog/mcp-permissions-securing-ai-agent-access-to-tools

cerbos.dev