helix-mcp-knowledge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BMC_DOCS_PASSWORD | No | Password for basic authentication to restricted BMC documentation pages. Optional; only needed for restricted pages. | |
| BMC_DOCS_USERNAME | No | Username for basic authentication to restricted BMC documentation pages. Optional; only needed for restricted pages. | |
| HELIX_KNOWLEDGE_CONFIG | No | Path to the configuration file. If not set, the server discovers the per-user workspace automatically. Can also be supplied via the --config command-line option. |
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
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_docsB | Retrieve documentary evidence from official BMC knowledge and the effective project. all_relevant never searches unrelated projects. |
| get_sectionB | Return a selected chunk and adjacent active chunks from the same document. Project sections require that project to be active or passed explicitly. |
| list_productsA | List configured or indexed BMC products; indexed is false until searchable evidence exists. |
| list_versionsA | List configured or indexed versions for one canonical or aliased BMC product; indexed is false until searchable evidence exists. |
| list_projectsB | List selectable projects and their BMC product versions without document content. |
| get_active_projectA | Return the project selected in this stdio server instance. |
| set_active_projectA | Select a project in this stdio server instance. Pass null to return to official-only. |
| get_update_statusA | Return the cached release status. Pass refresh=true to perform a read-only GitHub check; this tool never installs an update. |
| get_sync_statusB | Report official index readiness and synchronization state; project details are limited to the explicitly requested or active project. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have clearly distinct roles (active-project management, status checks, search, section retrieval, and listing). The main ambiguity is among the three list_* tools—list_projects, list_products, and list_versions—which describe related catalog concepts and could be confused since list_projects also mentions product versions, but the descriptions do provide enough distinction to disambiguate.
All nine tools follow a consistent snake_case verb_noun pattern (list_projects, get_active_project, set_active_project, get_update_status, get_sync_status, search_docs, get_section, list_products, list_versions). The verbs are also predictable and semantically appropriate (list_ for enumeration, get_ for retrieval, set_ for mutation).
Nine tools is well-scoped for a knowledge/retrieval server covering project selection, product/version discovery, status reporting, and document search/retrieval. Each tool appears to earn its place without redundancy.
The surface covers discovery (projects, products, versions), configuration (set/get active project), status, search, and section-level navigation, which is a coherent read-oriented lifecycle. Minor gap: there is no tool to enumerate documents within a project or fetch an entire document, so users must rely on search_docs plus get_section chunking.