Skip to main content
Glama
kauzy7

F5 AI Security Docs MCP Server

by kauzy7
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_docsA

Search the F5 AI Security documentation and return ranked results.

Indexes the entire docs.aisecurity.f5.com site (system overview, getting started/installation, application & API docs, the full REST API reference, integrations, red-team campaigns, use cases, glossary, and release notes).

Use this to find relevant F5 AI Security documentation for any question about scanners, providers, projects, campaigns, the API, deployment, etc.

Args: query: Search query string (e.g. "create a custom scanner", "openai compatibility", "guardrails pii", "get scans endpoint"). k: Maximum number of results to return (default: 5).

Returns: List of dictionaries containing: - url: Document URL - title: Display title - score: Relevance score (higher is better) - snippet: Contextual content preview

fetch_docA

Read F5 AI Security documentation pages with smart sectioning.

Modes:

  1. Catalog mode (omit uri): returns all available document URLs+titles.

  2. TOC mode (uri, no section): returns the page preamble plus a table of contents with section IDs, titles and summaries.

  3. Section mode (uri + section): returns the full content of one section identified by its TOC ID (e.g. "3" or "3.2").

Small documents (under ~8KB) are returned in full regardless of mode.

Recommended workflow:

  1. search_docs("your query") - find relevant URLs

  2. fetch_doc(uri="...") - see structure, preamble and section summaries

  3. fetch_doc(uri="...", section="3") - read the section you need

Args: uri: Document URL (must be under https://docs.aisecurity.f5.com/). If empty, returns a catalog of all available document URLs. section: Section ID from the TOC (e.g. "3" or "3.2"). Omit to get the table of contents.

Returns: Catalog / TOC / section payload, or an error dict on failure.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
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

TDQS

A4.6/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: fetch_doc retrieves documentation content (catalog, TOC, or section), while search_docs finds relevant documents via search. There is no overlap.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern (fetch_doc, search_docs), using snake_case and parallel structure.

Tool Count3/5

With only 2 tools, the server is on the low end of the acceptable range. While they cover search and retrieval, a typical documentation server might include additional tools like list_docs or get_doc_metadata.

Completeness5/5

The tools cover the full lifecycle for documentation consumption: search to find documents, fetch_doc to browse catalog, get TOC, and read sections. There are no obvious gaps for the stated purpose.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources