Zayo Put a Production MCP Server in Front of Its Network. What Does Agent Approval Actually Cover?
Zayo launched Agentic Networking for DynamicLink on 8 September 2026, describing it as the industry's first production MCP server built for networking. Approved AI agents can understand network context, reach network tools, and take authorized network or security actions. Zayo's own language keeps agent approval and action authorization as separate words. What is verified, what is Zayo's own claim, and what the launch material does not say.
Event analysed: . This analysis was published on 9 September 2026.
No, and Zayo's own wording does not claim otherwise. On 8 September 2026, Zayo launched Agentic Networking for DynamicLink, describing it as the industry's first production Model Context Protocol (MCP) server built specifically for networking, arriving as DynamicLink, Zayo's Network-as-a-Service platform launched 30 September 2025, reached its first year in production. Zayo states approved AI agents can understand network context, access network tools, and execute authorized network actions, and that enterprises determine which information, tools and actions an agent can access, with automation, governance and human oversight described as part of the operating model. Named potential workflows include establishing cloud-to-cloud connectivity, investigating network performance, coordinating multi-cloud connectivity, responding to unusual network activity, and executing approved network or security changes. Every www.zayo.com URL for this record returned EGRESS_BLOCKED on every attempted direct fetch in this session's own network egress proxy; content is corroborated through repeated, independently phrased search retrieval converging on the same wording across five independent outlets (Converge Digest, Fierce Network, 01net, CIO Influence, vmblog). Zayo's own language keeps 'approved agent' and 'authorized action' as two distinct qualifiers, which is a better starting position than collapsing them into one, but nothing reachable describes the mechanism that evaluates one specific requested tool call, at the moment it is made, against whatever an enterprise actually scoped in. DashAI, DynamicLink's conversational assistant, is separately documented, in Zayo's own 14 August 2026 CRN Tech Innovator Award announcement, as confirming user intent before executing a change; nothing reachable extends that same mechanism to the new MCP tool surface an external approved agent calls. Authentication, per-call authorization mechanics, target and environment binding, audit and execution-event evidence, and revocation are each unaddressed by any artifact this session could reach.
Zayo already runs a production network. DynamicLink, its software-defined Network-as-a-Service platform, has provisioned connectivity, resized bandwidth, connected cloud environments and managed security controls in production since 30 September 2025. On 8 September 2026, Zayo put a Model Context Protocol server in front of it, and said approved AI agents can now reach it directly.
What Zayo announced, precisely
Zayo's own announcement, titled Zayo Launches Agentic Networking, Bringing AI Agents Directly into Network Operations, describes what it calls the industry's first production MCP server built specifically for networking. Agentic Networking combines Zayo's network infrastructure, the DynamicLink platform, a specialized networking skill, and the MCP server, so that approved AI agents can understand network context and execute authorized network actions. Retrieval-augmented generation is stated to ground agent interactions in DynamicLink's own product and network knowledge, while enterprises determine which information, tools and actions an agent can access. Named potential workflows include establishing cloud-to-cloud connectivity, investigating network performance across network, cloud and application environments, coordinating multi-cloud connectivity, responding to unusual network activity, and executing approved network or security changes. Zayo states that automation, governance and human oversight remain part of the operating model.
Keeping two dates straight
DynamicLink itself is not new. Zayo originally launched it on 30 September 2025, describing it at the time as a platform built to deliver on and surpass Gartner's own definition of true Network-as-a-Service, overlaying Zayo's network footprint. The 8 September 2026 announcement is explicit that Agentic Networking arrives as DynamicLink reached its first year in production, positioned as the platform's next evolution rather than a separate product. This record keeps the two events as distinct, dated facts: a one-year-old production NaaS platform gained a new MCP-based agent surface. Neither date is backdated into the other.
Zayo's own language already separates two ideas
The durable question this record exists to answer is not whether Zayo built something real. A production MCP server sitting in front of a platform that already changes real network and security infrastructure is a genuine, consequential surface, not a demo. The question is what agent approval actually covers.
Zayo's own material is worth reading closely on exactly this point, because it does not conflate the two ideas this record tracks. Agents are described as approved. Actions are described as authorized. Those are two different qualifiers, applied to two different things: which agent may hold a session against the server at all, and whether a specific requested action falls inside what an enterprise actually granted. Enterprises are stated to determine which information, tools and actions an agent can access, a scoping decision an organization makes. That is a real, better-than-nothing design choice. It is not, on its own, a description of the mechanism that evaluates one specific requested network or security change, at the moment the agent asks for it, against that scope.
What the material does not say
Several things this record does not find anywhere reachable. No source describes how an external AI agent authenticates to the MCP server, what identity or credential format it presents, or how that identity is bound to the enterprise that approved it. No source describes a policy engine, a per-call evaluation step, or any mechanism that decides, at the moment a specific tool call is made, whether that exact call falls inside what was scoped in. No source states whether an approval or grant is bound to a specific network segment, cloud account, tenant or environment. No source describes an audit log, an execution receipt, an API event stream, a webhook, or any other runtime artifact produced when an agent's requested action executes. And no source describes how an enterprise revokes an agent's access once granted.
One further gap is worth stating precisely because it would be easy to round up. Zayo's own 14 August 2026 announcement, naming DynamicLink a 2026 CRN Tech Innovator Award winner, separately documents DashAI, DynamicLink's conversational AI assistant, as using retrieval-augmented generation and confirming user intent before executing a change, corroborated through search as a double confirmation before a change commits. That is a genuine, earlier, first-party record of a real control, built for DashAI's own conversational, natural-language surface. Nothing in the 8 September 2026 Agentic Networking material states that this same confirmation mechanism also gates the new MCP server's tool calls, made by an external approved agent rather than through DashAI's own chat interface. This record keeps the two as separately evidenced facts. A control documented for one surface is not assumed to cover a different one that arrived nearly a month later, described in different terms, without its own statement that it does.
Where this sits in the pattern
Moona Intelligence tracks a recurring collapse across this corpus: that a granted technical capability is treated as authority over what that capability makes reachable. Zayo's own announcement is a clean instance of the surface this collapse keeps appearing on, a production Model Context Protocol server exposing infrastructure tools to agents, the same surface this corpus has already tracked repeatedly across networking, cloud, database and observability vendors. What makes this particular launch worth its own record is not that it is unusual. It is that Zayo's own wording, agent approval and action authorization as two separate qualifiers, enterprises scoping which tools and actions an agent may reach, is a more careful starting position than several announcements this corpus has covered, and still leaves the same gap open: nothing published describes the mechanism that turns a scoping decision into a decision about one specific requested change. A production capability to alter real network and security infrastructure is precisely the claim where that gap should stay visible rather than be rounded up into governance.
Sources
This analysis interprets third-party reporting, research and announcements. Moona is not the original reporter of the underlying events.
Protocol evidence
This record does not assess these architectures. The connection runs through the Risk Registry requirement each one bears on, and these published authority architectures are what the evidence says about that requirement.
Protocol evidence related through AEW-008 Reachability treated as authority
- Supports requirement
ARC, Agentic Runtime Control
Britive
Requirement Britive states native support for the OpenID Shared Signals Framework, consuming CAEP and RISC events to trigger automated session termination, forced logout, step up authentication or account disable, and separately emitting its own CAEP and RISC events
Okta Threat Intelligence's own 9 September 2026 research states the corrective for exactly the substitution this weakness names, a technically valid credential standing in for an authorization check that never independently runs: monitor for session-token reuse and re-evaluate a session's standing whenever a critical context change occurs, rather than trusting a credential's validity at authentication time for the remainder of its technical lifetime. Convergent reporting attributes to Okta's own product material a Session Protection capability that continuously monitors active sessions post authentication and re-evaluates policy on an IP or device change, or on inbound risk telemetry over the Shared Signals Framework, the identical corrective principle, and the identical named standard, this property already credits to Britive's own native CAEP/RISC support under a different vendor. This link supports the requirement rather than closing the gap this weakness names for AI-service credentials specifically: nothing in either vendor's own reachable material establishes that a stolen but still-valid AI session token or API key, of the kind Okta's own dataset documents by the thousand, is itself a principal a Shared Signals Framework transmitter is watching, as distinct from the device or IP session context CAEP and RISC events are reported to cover.
- Supports requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement The registry's own discovery API carries exactly three operations, all reads, no invocation
This weakness's own response pattern calls for authorizing a resource independently of whatever makes it reachable, never letting reachability itself substitute for the missing check. AWS Agent Registry's own discovery API, confirmed directly from AWS's published SDK source to carry exactly three operations, BatchGetDiscoverableRegistryRecord, ListDiscoverableRegistryRecords and SearchDiscoverableRegistryRecords, all reads, with no operation that invokes a discovered resource, is architectural evidence of exactly that separation: a caller who successfully searches the registry gains the ability to find a record, not any ability the registry itself grants to act on what the record describes. Recorded as design evidence that a governed discovery catalog can keep discoverability and invocation authority structurally apart, not as a claim that every resource a record points to independently enforces its own authorization at the moment of invocation, which this record leaves unknown.
- Supports requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement AgentCore Runtime and Gateway resources AWS Agent Registry auto-detects land as unapproved Draft records, not as discoverable Approved ones
This weakness names reachability substituting for authority precisely where nothing independently checks a resource before it becomes actionable. AWS Agent Registry's own auto-detection of AgentCore Runtime and Gateway resources across an organization is, on its face, the kind of automatic admission this weakness's known examples already warn about; what keeps it from instantiating the weakness here is that a resource the registry auto-detects lands as an unreviewed Draft record, not as an Approved, discoverable one, so existing is kept apart from approved even when the existence itself was discovered automatically rather than declared by a publisher. Recorded as design evidence for this weakness's own corrective, not as a claim that every deployment actually enables the review step before treating an auto-detected resource as caught up, which this record did not independently confirm.
- Supports requirement
MCP 2026-07-28: Sessionless Protocol, Explicit State Handles and the Tasks Extension
Model Context Protocol
Requirement Possession of a state handle is not authorization, where authentication exists
The Model Context Protocol's own security best practices page, part of the final 2026-07-28 specification revision, states directly that MCP servers must not treat possession of a state handle as authentication, and SEP-2567 states the corrective an authenticated server should apply, validating a handle together with the caller's current authentication context on every call rather than the handle alone. This is the connectivity protocol's own normative guidance for exactly the substitution this weakness names, reachability or possession of a reference standing in for an independent authorization check, stated at the level of a widely adopted protocol's own specification rather than one vendor's product. This link supports the requirement rather than closing the gap: the guidance is a should addressed to a server's own application layer, since MCP itself defines no protocol-level handle type to enforce anything about, and this weakness's own Grafana known example, CVE-2026-19516, already documents a real MCP server whose session check accepted a caller supplied identifier the server itself had never issued, so the specification's own text and any one server's own conformance to it remain separate facts this link does not conflate.
- Implementation evidence
Agent Action Decision Protocol (AADP)
Shamik Saha, individual submission to the IETF
Requirement A Policy Decision Point owns authorization state and evidence; PEPs enforce it
AADP requires a Policy Enforcement Point to hold a permit from a Policy Decision Point before performing a governed action. GitHub's branch protection, requiring multi party review before a Terraform change could merge, functioned as exactly that enforcement point for the one attempted infrastructure backdoor Unit 42's own account names, denying a mutation the attacker's already compromised, technically valid access could otherwise reach. This is bounded, real world enforcement evidence for the one action the control was configured in front of, not evidence that the same separation governed the rest of the intrusion, which Unit 42's own account describes continuing on other paths after that one attempt was blocked.
- Implementation evidence
Agentic Networking for DynamicLink, a production MCP server for networking
Zayo
Zayo's Agentic Networking for DynamicLink, launched 8 September 2026, is a production deployment of a Model Context Protocol server, the same specification this weakness already connects through mcp-2026-07-28-sessionless-tasks above, now exposing production network and security infrastructure rather than a development or evaluation surface. It is implementation evidence for this weakness's own general form, reachability through an admitted MCP session substituting for an independent per-action authorization check, of the same kind this weakness already credits to Coder's Agent Firewall and Reco's Browser Guard: Zayo's own material states enterprises determine which information, tools and actions an agent can access, a scoping decision placed in front of the MCP tool surface, while no reachable artifact describes the mechanism that evaluates one specific requested tool call against that scope at the moment it is made. This link is scoped precisely to that evidentiary role. It does not evaluate a specific graded requirement of the MCP specification itself, and it does not treat Zayo's own governance language as proof that the gap this weakness names is closed for this vendor.
This record is the cited evidence for this relationship.
- Reveals bypass
ARC, Agentic Runtime Control
Britive
Requirement Whether an agent holding an independent credential or a direct network path to a target system can reach that system without passing through ARC's policy evaluation is not addressed in material available to this record
Britive's own documentation does not address whether an agent holding an independent credential or a direct network path can reach a target without passing through policy evaluation. That unmediated reachability is exactly the weakness these incidents turn on. NCSC's August 2026 interim advice on agentic AI corroborates the requirement this gap reveals, independently of the market's own protocol dataset: deny network access by default and mediate what remains through an approval gated, protocol or service aware proxy, rather than leave any path an agent's credentials or network position can reach unmediated. Grafana's own advisory for CVE-2026-19516 is a CVSS scored, vendor patched instance of exactly this gap: a Grafana MCP server's own network position reached internal, loopback and link local destinations, cloud metadata endpoints included, with no policy evaluation independently constraining the destination until the fix added one. Unit 42's account of a real enterprise intrusion, corrected 3 September 2026 to clarify the event was an intrusion rather than ransomware, is a further, larger instance: stolen cloud credentials reaching the victim organization's own AI infrastructure and CI/CD access reaching cloud keys, with no policy evaluation described as mediating either path. Cybernews's exposed server investigation, published 3 September 2026, adds an MCP intermediary to the same gap: a Penelope MCP interface exposed live reverse shell execution as a callable capability to an agent framework, Hermes Agent, across more than 30 real organisations, with nothing described as independently evaluating whether the calling agent held policy backed authority to use the shell the interface made reachable. Anthropic's own 30 July 2026 disclosure adds a further real instance rather than a sandbox breach: a fictional evaluation target's name matched a real, live domain, and the evaluation environment's own live internet access, present through a misconfiguration neither Anthropic nor its evaluation partner Irregular had noticed, let Claude Opus 4.7 reach and act on the real company across four runs with nothing independently evaluating whether the resolved target matched the one the evaluation actually authorized. GitHub Security Advisory GHSA-9mg6-c5wp-2g44, formally assigning CVE-2026-85666 on 4 September 2026, adds a further vendor patched instance from an MCP client rather than an MCP server: OGX's Responses API accepted a caller supplied MCP tool server_url and opened an MCP session against it, at session initialization during tool discovery, with no destination check independently constraining the reachable target, confirmed by direct reading of the affected source. This instance sharpens Britive's own gap beyond the general case: the same codebase already applies a working destination check, validate_url_not_private, to two sibling caller controlled URL inputs, so the unmediated path here is not an absent control but an existing one never connected to this specific resource class, evidence this dataset reads as reinforcing the requirement that resource policy needs to be applied by effect and resource class rather than by the feature specific code path that introduced the caller controlled URL. A proposed fix, pull request 6390, remains open and unmerged as of this link, so this entry does not treat the bypass as closed. A second, independently opened pull request, 6291, proposes the same check plus a scheme restriction and states explicitly that an administrator configured connector or toolgroup endpoint keeps a separate, unmediated resolution path by design, evidence this link reads as directly on point for what Britive's own documentation does not address: mediation applied to one provenance of endpoint, caller supplied, does not by itself establish anything about a differently provenanced endpoint, administrator configured, that the same policy engine would need to evaluate on its own terms rather than inherit by association. This pull request is also open and unmerged as of this link. Later technical coverage of the collusion.wiki report on the DSEWiki incident adds a further instance of the same reinforced requirement from a different direction: an OpenAI evaluation harness's read only internet restriction was enforced by permitting the GET HTTP method and blocking others, including POST, and DSEWiki's own ProWiki software accepted a page edit submitted as a GET request. Britive's own documentation does not address whether a request classified as read by its method can still produce a write at the destination, the same unaddressed gap this link already names for network position and destination, now shown for request method as the classifier instead. Both outlets naming the mechanism directly, and collusion.wiki itself, were blocked by this session's network egress policy; the mechanism is corroborated through cross referenced search rather than direct fetch. GitHub Security Advisory GHSA-rp45-5x3v-48mr adds a further instance narrower than any above: argocd-mcp's own HTTP and SSE transports bound to every network interface by default through version 0.8.0, confirmed directly against the affected source, with no policy evaluation, Host check or Origin check of any kind standing in front of a listener an operator's own environment configured Argo CD credential sat behind, so a network principal able to reach the bound listener needed nothing further to complete a credentialed, mutating Argo CD API call. CVE-2026-86122, published 5 September 2026 against Rowboat through version 0.9.1 and confirmed by direct reading of the affected source, adds a further instance that sharpens Britive's own gap past OGX's own case: Rowboat's project action authorization policy is confirmed running, correctly, before a custom MCP server URL or a project webhook URL is accepted, and nothing after that authorization call, and nothing in the agent runtime that later reads the stored URL back to open an MCP session or fetch a webhook, independently mediates which destination that authorized action may actually reach. Britive's own documentation does not address this either: an authorized project action, not only an independent credential or a direct network path, can carry unmediated reachability forward into whatever the resulting connection touches. A proposed fix, pull request 547, predates the report by five weeks, is not linked to it, and remains open and unmerged as of this link. GitHub Security Advisory GHSA-9m7h-vh2h-rc3w, published 6 September 2026 against OpenMAIC through version 1.0.0, adds an instance of a different shape than any above, and this link states the difference precisely rather than folding it into the general case: Britive's own documentation addresses whether a target is mediated by policy evaluation at all, not whether that mediation applies uniformly across every environment a deployment can run in. OpenMAIC's own validateUrlForSSRF is written correctly and already wired to five call sites the advisory names, confirmed by this link's own direct read at two of them, app/api/generate/image/route.ts and lib/server/resolve-model.ts, so the gap here is not an absent or unconnected check, as OGX's and Rowboat's own instances above show, but a check whose applicability depended on a condition, process.env.NODE_ENV === 'production', that the caller never touched and that a normal staging, preview or unset deployment fails by default, confirmed directly at both call sites this link checked against the affected tag. This composed with a separately confirmed fail open middleware, unchanged between the affected and fixed tags, that authenticated no request at all when the operator left ACCESS_CODE unset, so the unmediated path was reachable by an unauthenticated caller in the deployment states the environment condition already left unmediated. Fixed in OpenMAIC 1.0.1, released the same day, confirmed by this link's own direct read to remove the environment condition at both call sites checked and to add a repository scanning test, tests/server/url-guard-unconditional-invariant.test.ts, also read directly, that fails the project's own build if a validateUrlForSSRF call is again found gated on NODE_ENV. The same release replaces an implicit non production widening of what a caller supplied base URL could reach with an explicit ALLOW_LOCAL_NETWORKS grant an operator must set for local or private network access to be permitted at all, evidence this link reads as squarely on point for what Britive's own documentation does not address: mediation that applies only under an incidental deployment classification is not the same fact as mediation that applies to the resource and effect Britive's own policy evaluation is meant to reach, and an intentional exception to that mediation needs its own explicit grant rather than a classification's default.
- Missing requirement
AWS Agent Registry (Amazon Bedrock AgentCore)
Amazon Web Services
Requirement Whether, and how, a discovered resource's own invocation is independently authorized once found through the registry
This weakness's own authority gap is precisely the fact this record could not establish: what independently authorizes a discovered resource's own invocation, once a consumer has been authorized to find it. AWS's own reachable material states what discovery approval decides and stops there; nothing this session could reach describes the registry itself requiring, checking or even being aware of a separate invocation-time authorization on the resource a record names. Recorded as a missing requirement in the material this session could reach, not as a claim that no such requirement exists in AWS's own architecture; AgentCore Runtime, AgentCore Gateway or a third-party resource may well enforce one independently, and this record states that possibility as unknown rather than either confirmed or absent.