iac-copilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_URL | Yes | PostgreSQL connection string for the pgvector database that stores the security corpus and embeddings. | |
| LLM_PROVIDER | No | LLM provider used by the scan agent: `stub` (default, no API key), `anthropic`, `openai`, or `ollama`. | stub |
| OPENAI_API_KEY | No | Required when `LLM_PROVIDER=openai` or when `EMBEDDING_PROVIDER` is set to an OpenAI embedding model. | |
| ANTHROPIC_API_KEY | No | Required when `LLM_PROVIDER=anthropic`. | |
| EMBEDDING_PROVIDER | No | Embedding provider used for retrieval: `bge-small` (default), `openai-small`, or `openai-large`. | bge-small |
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_corpusA | Hybrid (BM25 + dense + RRF) retrieval over CIS AWS Foundations and OWASP CI/CD Top 10 guidance. Returns the top-k matching chunks with document title, heading path, URL and verbatim content for citation. |
| scan_terraform_planA | Run the LangGraph scan agent against a Terraform plan JSON (output of |
| list_sourcesA | Return document and chunk counts grouped by source. Useful to verify the corpus an agent is grounding answers in before trusting its citations. |
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 3 tools
Each tool serves a clearly distinct purpose: searching the guidance corpus, scanning a Terraform plan, and inspecting corpus sources. There is no overlap or ambiguity between them.
All tool names follow the same snake_case verb_noun pattern: search_corpus, scan_terraform_plan, list_sources. This is consistent and predictable.
Three tools is on the lower end but still within the well-scoped range. Each tool earns its place for the server's focused IaC copilot purpose.
The core workflow of searching guidance, scanning a plan, and verifying corpus sources is covered. Minor gaps exist such as no direct tool for retrieving a full document or listing supported scan rules, but these are not major dead ends.