Skip to main content
Glama
Sign In

NetActuate

by com.netactuate
OverviewDiscussionsAdmin

Search NetActuate's API reference

find_api_endpoints
Read-only

Searches the documentation of NetActuate's API (the API reference at netactuate.com/docs) for endpoints by what they do: 'create a virtual machine', 'list BGP sessions', 'firewall rules', 'DNS records', 'Kubernetes cluster'. It only reads that documentation: it never calls NetActuate's API and cannot change anything. Every word must match (filler such as 'a' or 'API' is ignored), read in the API's own terms ('VM' finds cloud server endpoints first, 'create' finds build ones), and the verb weighs the documented method; with no query it lists endpoints limit at a time. Each result gives the documented HTTP method, path, one-line summary, API version (v2 or v3; both are current, v3 for the newer resources) and the URL of its reference page, where the parameters and request body are; count is the full number of matches. Balancer's API (traffic routing, in beta) is included, its endpoints labelled api 'Balancer'; naming Balancer in the query, or api, searches only it. Use for 'how do I do X with the NetActuate API'. For how-to guides, Terraform and Ansible: search_netactuate or get_netactuate_doc.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_api_endpoints"
  }
}

Input Schema

NameRequiredDescriptionDefault
apiNoOnly one API: 'netactuate' (NetActuate's own, v2 and v3) or 'balancer' (Balancer's, in beta).
limitNoHow many endpoints to return, 1 to 50.
queryNoWords that must all appear in the endpoint's path, summary or description, e.g. 'server', 'bgp sessions', 'firewall', 'dns record'.
versionNoOnly this API version: v3 for VPC, Kubernetes, cloud routers, storage, firewalls and secrets; v2 for the rest.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / api
      Added value: +{
+  "description": "Only one API: 'netactuate' (NetActuate's own, v2 and v3) or 'balancer' (Balancer's, in beta).",
+  "enum": [
+    "netactuate",
+    "balancer"
+  ],
+  "type": "string"
+}
  2. Changed1 schema field changed
    • removedInput schema / properties / method
      Removed value: -{
-  "description": "Only this HTTP method, e.g. POST to create or GET to read.",
-  "enum": [
-    "GET",
-    "POST",
-    "PUT",
-    "PATCH",
-    "DELETE"
-  ],
-  "type": "string"
-}
  3. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  4. Changed1 schema field changed
    • removedInput schema / additionalProperties
      Removed value: -false
  5. Changed2 schema fields changed
    • changedInput schema / properties / method / description
      Previous value: -"Only this HTTP method."New value: +"Only this HTTP method, e.g. POST to create or GET to read."
    • changedInput schema / properties / version / description
      Previous value: -"Only this API version."New value: +"Only this API version: v3 for VPC, Kubernetes, cloud routers, storage, firewalls and secrets; v2 for the rest."
  6. Added

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/openWorld=false annotations, it discloses that the tool never calls the API and cannot change anything, explains exact matching behavior (all words must match, filler like 'a'/'API' ignored, API-native terminology mapping), states the default listing behavior when query is empty, and describes the result fields and the meaning of count. This is unusually rich behavioral context that annotations alone would not convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose and the read-only guarantee, then matching behavior, then result shape, then routing to alternatives. It is dense — several long compound sentences — but nearly every clause carries information an agent needs; only minor tightening is possible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by enumerating what each result contains (HTTP method, path, summary, API version, reference URL) and what count means. Combined with the matching and scoping rules, an agent has everything needed to call it correctly and interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning: query is AND-matching with filler words ignored and API-specific term weighting, limit governs the no-query listing size, and the api parameter can be implied by naming Balancer in the query. Version semantics are mostly left to the schema, which already lists resource examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — searching NetActuate's API reference documentation for endpoints by what they do — and gives concrete example queries ('create a virtual machine', 'DNS records'). It immediately distinguishes itself from search_netactuate and get_netactuate_doc by scope (API reference only, not guides/Terraform/Ansible).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it ('Use for "how do I do X with the NetActuate API"') and routes the agent elsewhere for how-to guides, Terraform and Ansible via named siblings. It also explains the scoping effect of naming Balancer in the query or setting api, so the agent knows how to narrow results.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All NetActuate toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources