> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxa.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Praxa MCP use cases for developers and businesses

> Apply Praxa MCP tools to governed missions, capability discovery, memory recall, traces, goals, skills, and evidence workflows with safe boundaries.

Praxa MCP tools let an MCP-compatible agent host discover governed
capabilities, create and inspect durable missions, query purpose-filtered
memory, and read evidence surfaces. The contracts add a standard tool boundary;
they do not grant provider authority or make model prose an execution receipt.

## Choose a use case

| Outcome                                        | Tools                                                           | Audience                        | Completion evidence                                        |
| ---------------------------------------------- | --------------------------------------------------------------- | ------------------------------- | ---------------------------------------------------------- |
| Turn a request into a durable governed mission | `aura_submit_intent`, `aura_create_mission`, `aura_get_mission` | Product teams, operations       | Mission projection and terminal events                     |
| Interrupt or stop a mission safely             | `aura_signal_mission`, `aura_cancel_mission`                    | Operators, support              | Accepted signal/cancel request plus final mission readback |
| Discover eligible capabilities before planning | `aura_search_capabilities`                                      | Agent builders                  | Policy-eligible capability results, not model guesses      |
| Recall approved context for one purpose        | `aura_query_memory`                                             | Personalization and support     | Purpose/compartment-filtered results with provenance       |
| Load a governed reusable procedure             | `aura_get_skill`                                                | Developer platforms             | Exact skill version and evidence state                     |
| Explain what happened                          | `aura_get_trace`                                                | SRE, compliance, support        | Redacted causal trace correlated to the run                |
| Align work with current goals                  | `aura_list_goals`                                               | Assistants and planning tools   | Purpose-filtered goal list                                 |
| Inspect model and reference evidence           | `aura_list_world_certificates`, `aura_get_coverage`             | Evaluation and governance teams | Signed certificate or bounded coverage evidence            |

## Example: governed support escalation

1. Search capabilities for the escalation action family.
2. Query only the support compartment and incident-resolution purpose.
3. Submit the user intent with one stable idempotency key.
4. Create a bounded mission after the application validates the goal and budget.
5. Require host approval before any mutation.
6. Read the mission and trace until the required terminal evidence exists.
7. Store only redacted identifiers and receipts in the support case.

```mermaid theme={null}
flowchart LR
  Request["Support request"] --> Search["Search eligible capabilities"]
  Search --> Recall["Recall purpose-filtered context"]
  Recall --> Approval["Host and Praxa policy checks"]
  Approval --> Mission["Durable mission"]
  Mission --> Evidence["Projection, events, trace, receipt"]
  Evidence --> Review["Human-verifiable outcome"]
```

## Example: engineering incident assistant

Give the host read-only access to `aura_get_mission`, `aura_get_trace`,
`aura_get_skill`, and `aura_get_coverage`. Ask it to summarize an incident run,
cite the exact trace and skill version, and identify missing evidence. Do not
enable mission mutation tools until the read-only workflow passes isolation,
redaction, and prompt-injection tests.

## Example: enterprise capability catalog

Use `aura_search_capabilities` to populate a reviewed catalog of actions that
are policy eligible for a purpose and target type. Cache only within the
deployment's freshness rules. A search result is eligibility evidence, not
entitlement, provider availability, approval, or proof that an action ran.

## When MCP is not the best interface

* Use `@praxa/sdk` when your TypeScript service needs the complete mission client and event helpers.
* Use Execution Fabric `/v1` when a backend needs the minimal public durable-task contract.
* Use `@praxa/sdk/memory` when you are federating existing provider memory read-only.
* Use direct API reference calls for deterministic service-to-service flows that do not need a model to choose tools.

## Production acceptance

Test tool selection, correct and wrong scopes, revocation, tenant isolation,
prompt injection in returned content, schema rejection, approval visibility,
exact mutation replay, changed-body conflict, timeout reconciliation, output
bounds, audit correlation, and cleanup. See [security and testing](/mcp/security-and-testing).