harness_describe

MCP tool from MCP Server by harness

Discover available resource types, operations, and fields. No API call — returns local registry metadata.

How to use it

harness_describe is exposed by the MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the harness_describe tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install MCP Server

$claude mcp add harness -- npx harness-mcp-v2

FULL MCP SERVER LISTING

Other tools in MCP Server (21)

body

must be an object with a yaml field. Raw string bodies are rejected by the public harnessexecute schema.

branch

build.type=branch, build.spec.branch=<value>

commit_sha

build.type=commitSha, build.spec.commitSha=<value>

executionId

the plan execution ID from resourceid.

harness_create

Create a new resource. Supports inline and remote (Git-backed) pipelines. Prompts for user confirmation via elicitation.

harness_delete

Delete a resource. Prompts for user confirmation via elicitation. Destructive.

harness_diagnose

Diagnose pipeline, connector, delegate, and gitopsapplication resources (aliases: execution -> pipeline, gitopsapp -> gitopsapplication). For pipelines, returns stage/step timing and failure details; for connectors/delegates/GitOps apps, returns targeted health and troubleshooting signals.

harness_execute

Execute an action on a resource (run/retry pipeline, import pipeline from Git, toggle flag, sync app). Prompts for user confirmation via elicitation. For pipeline runs, use the runtime-input workflow below (supports branch/tag/prnumber/commitsha shorthand expansion).

harness_get

Get a single resource by its identifier.

harness_list

List resources of a given type with filtering, search, and pagination.

harness_schema

Fetch exact YAML/JSON Schema definitions and examples for creating/updating resources. Pipeline/template schemas are bundled; connector, environment, service, secret, and infrastructure schemas are scope-aware entity schemas fetched from bundled snapshots or NG /yaml-schema. Supports deep drilling v

harness_search

Search across Harness resource types with a single query. Uses semantic routing (local all-MiniLM-L6-v2 ONNX embeddings, 384-dim) to predict relevant resource types from a knowledge corpus indexed at startup — typically narrowing from ~163 types to 1–8 before scatter-gather. Falls back to full keywo

harness_status

Get a real-time project health dashboard — recent executions, failure rates, and deep links.

harness_update

Update an existing resource. Supports inline and remote (Git-backed) pipelines. Prompts for user confirmation via elicitation.

inputSetBranchName

source branch for Git-backed input sets, or null.

inputSetDetails

contributing saved input sets as { identifier, name } pairs.

inputSetTemplateYaml

input template at execution time, or null.

inputSetYaml

merged runtime input YAML used for the run, or null.

pr_number

build.type=PR, build.spec.number=<value>

resolvedYaml

expression-resolved YAML when resolveexpressions=true, otherwise usually null.

tag

build.type=tag, build.spec.tag=<value>