io.github.loopg/pramana-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PRAMANA_API_KEY | Yes | Your Pramana engineer or admin API key. Create a key in Settings → API keys at reliai.in. Engineer or admin key is required; an auditor key will not receive recorded prompts or responses. | |
| PRAMANA_API_URL | No | Optional custom Pramana API URL for self-hosting. Set this to your own API endpoint if you are not using the default hosted API. |
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 |
|---|---|
| list_tracesB | List recorded AI agent runs (traces) captured by Pramana, optionally filtered by agent, status or time range. |
| get_traceA | Get one recorded agent run: its steps, model calls, tool calls with arguments, and outcome. |
| list_model_diffsC | List comparison runs that checked a prompt or model change against recorded production runs. |
| get_model_diffB | Get the findings of one comparison run: which decisions changed behaviourally, which were cosmetic, and which runs halted. |
| verify_bundleB | Verify a Pramana signed evidence bundle offline, with no account and no network access. |
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 5 tools
Each tool has a clearly distinct purpose: two list/get pairs for traces and model diffs, plus an independent offline verification tool. There is no overlap between listing, retrieving, and verifying operations, so misselection is unlikely.
All five names follow a consistent snake_case verb_noun pattern (list_traces, get_trace, list_model_diffs, get_model_diff, verify_bundle). The list/get pairing is symmetric and predictable across both resources.
Five tools is well-scoped for an observability/inspection server with two resources plus a verification utility. Each tool earns its place with no redundant entries.
The list/get pairs cover discovery and detail for traces and diffs, and verify_bundle handles the evidence-checking lifecycle, so read workflows are complete. Minor gaps exist (e.g. no trace export or diff-creation trigger), but these are workable given the inspection-focused scope.