# io.opsera/opsera

> Opsera AI Agent MCP server providing authenticated DevOps automation over SSE

- name: io.opsera/opsera
- version: 0.5.0
- connection class: R1 (autonomous)
- trust: 81/100
- quality: 65/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.opsera%2Fopsera
- tools: https://api.protogrid.dev/v1/servers/io.opsera%2Fopsera/tools

**An agent can connect on its own if it already holds `OPSERA_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "opsera": {
      "type": "sse",
      "url": "https://agent.opsera.io/mcp",
      "headers": {
        "Authorization": "Bearer ${OPSERA_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${OPSERA_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 25
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% -stale-375d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 65/100 (needs work)

### protocol: 50 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- warn `protocol.transport`: only the legacy HTTP+SSE transport, deprecated until 2027-07-28
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: opsera_mappings (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); opsera_users (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); opsera_groups (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 4,211 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 11, about 4,211 tokens to load them all
- tool set hash: 5c17a1f289a79422843042524cd93beb
- tools last changed: 2026-10-09T19:05:57.160Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.opsera/opsera.svg)](https://protogrid.dev/servers/io.opsera/opsera)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-09 `opsera_pipelines` changed (inputSchema)
- 2026-10-08 `opsera_pipelines` changed (inputSchema)
- 2026-10-07 `opsera_pipelines` changed (inputSchema)
- 2026-10-02 `opsera_users` changed (description, inputSchema)
  - before: User management: get_current, get, list, create, delete. See docs/API_REFERENCE.md.
  - after: User management: get_current, get, list (optional active=true|false), create, delete. See docs/API_REFERENCE.md.
- 2026-10-02 `opsera_pipelines` changed (inputSchema)
- 2026-10-02 `opsera_pipeline_parameters` added
  - Pipeline parameters: reusable, configurable key-value pairs scoped to a pipeline. Parameters can be referenced by pipeline steps during execution for dynamic configuration (environment variables, secrets, build flags, deployment targets). Use list to see all parameters for a pipeline before triggering a run. Use create/update to set runtime values. Use get_value for lightweight value retrieval. Parameter types: string (default), number, boolean, secret (masked in logs). See docs/API_REFERENCE.md.

Full history: https://api.protogrid.dev/v1/servers/io.opsera%2Fopsera/changes

## Remotes

- https://agent.opsera.io/mcp (sse, auth api_key ${OPSERA_TOKEN}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (11)

- `opsera_groups`: Group management: list, get, create, delete, get_memberships, add/remove/patch members. See docs/API_REFERENCE.md.
- `opsera_insights`: Insights: dashboards, filters, audit logs, KPIs, tool mappings. See docs/API_REFERENCE.md for all operations.
- `opsera_mappings`: Data mappings: list, get, create, update. See docs/API_REFERENCE.md.
- `opsera_pipeline_parameters`: Pipeline parameters: reusable, configurable key-value pairs scoped to a pipeline. Parameters can be referenced by pipeline steps during execution for dynamic configuration (environment variables, secrets, build flags, deployment targets). Use list to see all parameters for a pipeline before triggering a run. Use create/update to set runtime values. Use get_value for lightweight value retrieval. Parameter types: string (default), number, boolean, secret (masked in logs). See docs/API_REFERENCE.md.
- `opsera_pipelines`: Pipelines: monitor runs, security audit, run duration stats, configuration, templates, and lifecycle actions. Execution questions (image tag, artifact, commit SHA): list_runs then get_run (view=artifacts by default). Do not call get afterward. security_audit: find pipelines with disabled security steps; set includeStats=true to include each pipeline average/min/max run duration. runs_stats: average/min/max run duration for one pipelineId or batch pipelineIds (no security filter). get with view=security audits one known pipeline; get without view is full config (large). list is a lightweight catalog. list_runs is recent run timing. action runs mutations. See docs/API_REFERENCE.md.
- `opsera_projects`: Projects: list, get, create, update. See docs/API_REFERENCE.md for operations.
- `opsera_reports_and_logs`: Reports and logs: reports_tasks_created, reports_pipelines_created, logs_audit_user, logs_task. See docs/API_REFERENCE.md.
- `opsera_search_data_settings`: Cross-entity discovery and platform settings. search finds pipeline, task, or registry records by name or ID and returns lightweight metadata only — not execution history, artifacts, durations, or full stage configuration (use opsera_pipelines for those). org_hierarchy and settings_tasks for organizational mapping and task configuration updates. See docs/API_REFERENCE.md.
- `opsera_tasks`: Tasks: list, create, status, lookup; lifecycle mutations via operation=action (run, stop, create, update, status). See docs/API_REFERENCE.md.
- `opsera_tools`: Tools & registry: identifiers, registry, scm_repositories, scm_branches, registry_configurations. See docs/API_REFERENCE.md.
- `opsera_users`: User management: get_current, get, list (optional active=true|false), create, delete. See docs/API_REFERENCE.md.