harness-mcp-v2 3.2.27 → 3.2.29

package/README.md

@@ -2,7 +2,7 @@
 
 [![MCP Toplist](https://mcptoplist.com/badge/glama%2Fharness%2Fmcp-server.svg)](https://mcptoplist.com/server/glama%2Fharness%2Fmcp-server)
 
-An MCP (Model Context Protocol) server that gives AI agents full access to the Harness.io platform through 11 consolidated tools and 247 resource types.
+An MCP (Model Context Protocol) server that gives AI agents full access to the Harness.io platform through 11 consolidated tools and 251 resource types.
 
 ## Why Use This MCP Server
 
@@ -10,8 +10,8 @@ Most MCP servers map one tool per API endpoint. For a platform as broad as Harne
 
 This server is built differently:
 
-- **11 tools, 247 resource types.** A registry-based dispatch system routes `harness_list`, `harness_get`, `harness_create`, etc. to any Harness resource — pipelines, services, environments, orgs, projects, feature flags, cost data, and more. The LLM picks from 11 tools instead of hundreds.
-- **Full platform coverage.** 41 default toolsets spanning CI/CD, GitOps, Feature Flags, Cloud Cost Management, Security Testing, Chaos Engineering, Database DevOps, Internal Developer Portal, Software Supply Chain, Infrastructure as Code Management, Release Management, Governance, Service Overrides, Knowledge Graph, and more. Opt-in Ansible coverage is available when you need inventory and playbook data.
+- **11 tools, 251 resource types.** A registry-based dispatch system routes `harness_list`, `harness_get`, `harness_create`, etc. to any Harness resource — pipelines, services, environments, orgs, projects, feature flags, cost data, and more. The LLM picks from 11 tools instead of hundreds.
+- **Full platform coverage.** 41 default toolsets spanning CI/CD, GitOps, Feature Flags, Cloud Cost Management, Security Testing, Chaos Engineering, Database DevOps, Internal Developer Portal, Software Supply Chain, Infrastructure as Code Management, Release Management, Governance, Service Overrides, Knowledge Graph, and more. Opt-in Ansible and observability-evaluation coverage is available when needed.
 - **Multi-project workflows out of the box.** Agents discover organizations and projects dynamically — no hardcoded env vars needed. Ask "show failed executions across all projects" and the agent can navigate the full account hierarchy.
 - **35 prompt templates.** Pre-built prompts for common workflows: build & deploy apps end-to-end, debug failed pipelines, review DORA metrics, triage vulnerabilities, optimize cloud costs, audit access control, plan feature flag rollouts, review pull requests, approve pending pipelines, and more.
 - **Works everywhere.** Stdio transport for local clients (Claude Desktop, Cursor, Devin Desktop), HTTP transport for remote/shared deployments, Docker and Kubernetes ready.
@@ -938,7 +938,7 @@ For v0 pipelines, use this sequence to reduce execution-time input errors:
   - **Constraint:** shorthand expansion is skipped when `inputs.build` is already present (explicit `build` wins).
 3. **Execute the run**
   - `harness_execute(resource_type="pipeline", action="run", resource_id="<pipeline_id>", ...)`
-  - For Git-backed pipelines whose YAML should be loaded from a non-default branch, pass `params.pipeline_branch` (sent to Harness as `pipelineBranchName`):
+  - For Git-backed pipelines whose YAML should be loaded from a non-default branch, pass `params.pipeline_branch` (sent to Harness as `branch`). This explicit definition selector takes precedence over the `params.branch` alias. `inputs.branch` independently selects the CI codebase branch:
 
     ```json
     {
@@ -1261,7 +1261,7 @@ Harness pipelines can be stored in three ways:
 
 ## Resource Types
 
-247 resource types organized across 41 toolsets. Each resource type supports a subset of CRUD operations and optional execute actions.
+251 resource types organized across 41 toolsets. Each resource type supports a subset of CRUD operations and optional execute actions.
 
 ### Platform
 
@@ -1364,7 +1364,7 @@ Both pipeline YAML resource types are available when the pipelines toolset is en
 
 | Resource Type    | List | Get | Create | Update | Delete | Execute Actions           |
 | ---------------- | ---- | --- | ------ | ------ | ------ | ------------------------- |
-| `delegate`       | x    |     |        |        |        |                           |
+| `delegate`       | x    | x   |        |        |        |                           |
 | `delegate_token` | x    | x   | x      |        | x      | `revoke`, `get_delegates` |
 
 
@@ -1376,13 +1376,15 @@ Both pipeline YAML resource types are available when the pipelines toolset is en
 | `repository`   | x    | x   | x      | x      |        |                      |
 | `branch`       | x    | x   | x      |        | x      |                      |
 | `commit`       | x    | x   | x      |        |        | `diff`, `diff_stats` |
-| `file_content` |      | x   |        |        |        | `blame`              |
+| `file_content` | x    | x   |        |        |        | `blame`              |
 | `tag`          | x    |     | x      |        | x      |                      |
 | `repo_rule`    | x    | x   |        |        |        |                      |
 | `space_rule`   | x    | x   |        |        |        |                      |
 
 `commit` creation commits one or more file actions directly through the Harness Code API without cloning. Pass `body.title`, `body.branch`, and `body.actions`; each action is `CREATE`, `UPDATE`, `DELETE`, or `MOVE`, and `UPDATE` requires the current blob SHA.
 
+`file_content` list returns every path at a ref; get returns file or directory content (omit or pass empty `path` for the repo root; nested paths keep slashes). Omit `git_ref` to use the repository default branch — do not guess `main`.
+
 
 ### Artifact Registries
 
@@ -1539,12 +1541,14 @@ IaCM list responses expose `page_count` as the count for the current page only (
 | -------------- | ---- | --- | ------ | ------ | ------ | --------------- |
 | `pull_request` | x    | x   | x      | x      |        | `close`, `merge` |
 | `pr_reviewer`  | x    |     | x      |        |        | `submit_review` |
-| `pr_comment`   | x    |     | x      |        |        |                 |
+| `pr_comment`   |      |     | x      | x      | x      |                 |
 | `pr_check`     | x    |     |        |        |        |                 |
 | `pr_activity`  | x    |     |        |        |        |                 |
 
 Use `harness_execute(resource_type="pull_request", action="close", ...)` for an explicit close operation. `harness_update` also accepts `body.state` (`open` or `closed`) and routes state changes to the dedicated Harness Code PR state endpoint; send title/description edits in a separate update call.
 
+Use `harness_list(resource_type="pr_activity", filters={type: ["comment", "code-comment"]}, ...)` to read PR comments. Use `pr_comment` for comment write operations.
+
 
 ### Release Management
 
@@ -1749,6 +1753,10 @@ In single-user/self-hosted mode, legacy-mode auth uses a Bearer token from `HARN
 | `cost_recommendation_stats`  |      | x   |        |        |        |                                                                                |
 | `cost_recommendation_detail` |      | x   |        |        |        |                                                                                |
 | `cost_commitment`            |      | x   |        |        |        |                                                                                |
+| `ai_budget`                  | x    | x   | x      | x      | x      |                                                                                |
+| `ai_budget_overview`         |      | x   |        |        |        |                                                                                |
+| `ai_budget_consumption`      | x    |     |        |        |        |                                                                                |
+| `ai_budget_override_request` | x    | x   | x      |        |        | `approve`, `reject`                                                            |
 
 
 ### Software Engineering Insights (SEI)
@@ -1824,7 +1832,7 @@ Security exemption execute workflow:
 | Resource Type     | List | Get | Create | Update | Delete | Execute Actions |
 | ----------------- | ---- | --- | ------ | ------ | ------ | --------------- |
 | `user`            | x    | x   |        |        |        |                 |
-| `user_group`      | x    | x   | x      |        | x      |                 |
+| `user_group`      | x    | x   | x      | x      | x      |                 |
 | `service_account` | x    | x   | x      |        | x      |                 |
 | `role`            | x    | x   | x      |        | x      |                 |
 | `role_assignment` | x    |     | x      |        |        |                 |
@@ -1943,10 +1951,11 @@ Security exemption execute workflow:
 
 ## Toolset Filtering
 
-By default, 41 of 44 toolsets are enabled. Three toolsets are opt-in and excluded from the defaults:
+By default, 41 of 45 toolsets are enabled. Four toolsets are opt-in and excluded from the defaults:
 
 - **`ansible`** — Harness Ansible (inventories, playbooks, hosts, activity). Opt-in because it is project-scoped and adds concepts many users do not need.
 - **`autonomous_work`** — Development Harness (autonomous work). Opt-in; see toolset description for scope.
+- **`observability-evaluations`** — Scheduled production-telemetry evaluation rules. Opt-in because it depends on the deployed scoring control plane.
 - **`registries-v3`** — Harness Artifact Registry v3 (packages, versions, files, metadata, scans, firewall exceptions). Opt-in until v3 writes land, so agents don't have to disambiguate between v1 registries/artifacts and v3 packages/versions.
 
 ### Adding toolsets with `+` prefix
@@ -2015,6 +2024,7 @@ Available toolset names:
 | `evidence-vault`        | attestation                                                                                                                                                                                                                                                                                     |
 | `sto`                   | security_issue, security_issue_filter, security_exemption, remediation_diff                                                                                                                                                                                                                     |
 | `dbops`                 | database_schema, database_instance, database_snapshot_object, database_llm_authoring_pipeline                                                                                                                                                                                                   |
+| `autonomous_work` *(opt-in)* | work_item, work_item_resume, work_item_approve, work_timeline, work_budget, work_phase, work_phase_artifact, work_artifact, budget, budget_grant, budget_usage, work_class, work_trigger, capability, risk_evaluator, team, member, member_template, software_component, content_source_connector |
 | `access_control`        | user, user_group, service_account, role, role_assignment, resource_group, permission                                                                                                                                                                                                            |
 | `governance`            | policy, policy_set, policy_evaluation                                                                                                                                                                                                                                                           |
 | `freeze`                | freeze_window, global_freeze                                                                                                                                                                                                                                                                    |
@@ -2023,6 +2033,7 @@ Available toolset names:
 | `knowledge-graph`       | kg_queryable_type_summary, kg_grammar, hql_query                                                                                                                                                                                                                                                |
 | `semantic-layer`        | kg_type, kg_related_type                                                                                                                                                                                                                                                                        |
 | `ai-evals`              | eval_dataset, eval_dataset_item, evaluation, eval_run, eval_run_item, eval_run_by_eval, eval_metric, eval_metric_set, eval_metric_set_entry, eval_suite, eval_suite_evaluation, eval_suite_run, eval_target, eval_annotation, eval_analytics, eval_git_settings, eval_registry_item, eval_git_registration, online_eval |
+| `observability-evaluations` *(opt-in)* | observability_evaluation_rule                                                                                                                                                                                                                                                    |
 | `iacm`                  | iacm_workspace, iacm_variable_set, iacm_resource, iacm_module, iacm_provider, iacm_workspace_costs, iacm_activity_resource_change                                                                                                                                                               |
 | `ansible` *(opt-in)*    | ansible_inventory, ansible_playbook, ansible_host, ansible_host_activity, ansible_activity                                                                                                                                                                                                      |
 | `registries-v3` *(opt-in)* | package_v3, version_v3, file_v3, registry_metadata_v3, package_metadata_v3, version_metadata_v3, file_metadata_v3, metadata_key_v3, metadata_value_v3, artifact_scan_v3, bulk_scan_evaluation_v3, firewall_exception_v3, firewall_exception_version_v3                                       |
@@ -2045,8 +2056,8 @@ Available toolset names:
                           |
                  +--------v---------+
                 |    Registry       |  <-- Declarative resource definitions
-                |  41 Toolsets      |      (data files, not code)
-                |  247 Resource Types|
+                | 45 Toolsets (41 default) |
+                |  251 Resource Types|
                  +--------+---------+
                           |
                  +--------v---------+
@@ -2346,7 +2357,7 @@ The Harness MCP server pairs well with **[Harness Skills](https://github.com/har
 | `Read-only mode is enabled ... operations are not allowed`                       | `HARNESS_READ_ONLY=true` blocks create/update/delete/execute                                         | Set `HARNESS_READ_ONLY=false` if write operations are intended                                                                       |
 | Pipeline run fails pre-flight with unresolved required inputs                    | Provided `inputs` did not cover required runtime placeholders                                        | Fetch `runtime_input_template`, supply missing simple keys, or use `input_set_ids` for structural inputs                             |
 | Pipeline CI shorthand (`branch`, `tag`, `pr_number`, `commit_sha`) did not apply | `inputs.build` was already provided, so shorthand expansion was intentionally skipped                | Remove `inputs.build` to use shorthand expansion, or keep full explicit `build` structure                                            |
-| Pipeline run loaded the wrong YAML revision                                     | The pipeline definition is stored in Git and the run did not specify the desired pipeline branch      | Pass `params.pipeline_branch` on the `run` action; this maps to Harness `pipelineBranchName`                                         |
+| Pipeline run loaded the wrong YAML revision                                     | The pipeline definition is stored in Git and the run did not specify the desired pipeline branch      | Pass `params.pipeline_branch` on the `run` action; this maps to Harness `branch`                                                     |
 | `wait: true` returned `_wait.error`                                              | The pipeline trigger succeeded, but server-side polling failed                                       | Recheck the `execution_id` with `harness_get(resource_type="execution", ...)` before deciding whether to rerun                        |
 | `wait: true` returned `execution_timed_out: true`                                | The execution did not reach a terminal status before `wait_timeout_seconds`                          | Use the returned `execution_id` to recheck status; wait for a terminal status before running `harness_diagnose`                       |
 | Execution logs are empty or blob downloads return 403                           | Harness-hosted log blob URLs require the configured Harness client/auth path, especially for internal or self-managed hosts | Keep `HARNESS_BASE_URL` pointed at the target Harness host and use `harness_get(resource_type="execution_log", ...)` or `harness_diagnose(..., include_logs=true)` rather than bypassing the MCP client |

package/build/data/schemas/v0/pipeline.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../../../../src/data/schemas/v0/pipeline.ts"],"names":[],"mappings":"AAGA,QAAA,MAAM,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CA2vzH/B,CAAC;AACF,eAAe,MAAM,CAAC"}
+{"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../../../../src/data/schemas/v0/pipeline.ts"],"names":[],"mappings":"AAGA,QAAA,MAAM,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,GAAG,CA2h0H/B,CAAC;AACF,eAAe,MAAM,CAAC"}