Skip to main content
Glama
harness

Harness MCP Server

Official
by harness

harness_list

Read-only

List Harness resources using filters, search, and pagination. Provide a URL to auto-extract scope or specify org/project identifiers.

Instructions

List Harness resources with filtering and pagination. Accepts a Harness URL to auto-extract scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoHarness UI URL — auto-extracts org, project, and type
pageNoPage number, 0-indexed
sizeNoPage size (1–100). Some resource types enforce a lower max (e.g. security_exemption max 50) — call harness_describe for per-resource limits.
org_idNoOrganization identifier (overrides default)
paramsNoAdditional identifiers for nested resources (e.g. repo_id for pull requests). Call harness_describe for fields per resource_type.
compactNoStrip verbose metadata from list items, keeping only essential fields (default true)
filtersNoResource-specific filters as key-value pairs. Available keys across enabled resource types: search_term, module, filter_type, pipeline_id, status, branch, my_deployments, execution_id, approval_status, approval_type, node_execution_id, sort, order, env_type, type, category, connector_names, connector_identifiers, connectivity_statuses, connector_connectivity_modes, description, inheriting_credentials_from_delegate, tags, include_all_connectors_available_at_scope, environment_id, deployment_type, secret_identifier, secret_name, secret_manager_identifiers, include_all_secrets_accessible_at_scope, audit_resource_type, action, start_time, end_time, all, delegate_name, delegate_type, host_name, delegate_group_identifier, delegate_instance_filter, auto_upgrade, version_status, name, query, git_ref, path, since, until, committer, inherited, search, package_type, template_type, template_list_type, global, metadata_only, entity_type, folder_id, kind, scope_level, owned_by_me, favorites, owner, lifecycle, sort_type, sort_order, is_custom, entity_identifier, state, after, before, offset, workspace_id, rollout_status_id, segment_name, repo_creds_id, agent_id, app_name, namespace, resource_name, group, version, scope, experiment_name, infra_id, experiment_ids, start_date, end_date, target_network_map_ids, my_experiments, exclude_automation, probe_ids, infra_type, sort_field, sort_ascending, experiment_run_ids, notify_ids, hub_identity, infrastructure_type, infrastructure, include_all_scope, experiment_id, is_identity, include_legacy_infra, infra_scope, is_ai_enabled, is_enterprise, fault_id, permissions_required, only_templatised_faults, environment_type, minimal, agent_identity, severity, risk_rule_id, validation_type, service_identity, environment_identity, is_system, data_source, scan_type, pipeline_identity, cloud_filter, view_state, view_type, view_ids, folder_name_pattern, group_by, time_filter, limit, time_resolution, min_saving, days_back, recommendation_states, cost_category, cost_buckets, sort_by, perspective_id, anomaly_view, search_text, order_by_field, order_by_direction, min_amount, min_anomalous_spend, value_type, value_sub_type, is_cluster_query, is_cluster_hourly_data, search_key, page, size, aspect, integration_type, profile_id, team_ref_id, date_start, date_end, granularity, metric_type, artifact_type, source_id, artifact_id, dependency_type, oss_risk_filter, standards, enforcement_id, purl, drift_id, subject_name, subject_digest, types, sources, scopes, severity_codes, issue_types, target_ids, target_types, pipeline_ids, scan_tools, exemption_statuses, stages, steps, product_names, include_exempted, origins, origin_statuses, epss, epss_percentile, severity_overridden, reachability, exploitability, page_existing, page_size_existing, page_new, page_size_new, scan_id, validation_execution_id, only_true_positive, exclude_repo_patterns, migration_type, dbschema_id, dbinstance_id, object_type, principal_type, role_identifier, resource_group_identifier, include_parent_scopes, identifiers, sort_orders, page_token, has_module, module_type, only_favorites, identifier_filter, exclude_rego, include_policy_set_count, entity, created_date_from, created_date_to, include_child_scopes, freeze_status, service_id, target_id, dataset_id, metric_set_id, run_id, eval_id, set_id, suite_id, trace_id, label, annotator_type, tag, provider, activity_id, kinds, annotations, object_kind, impacted_service, environment, commander, text, reported_after, reported_before, sort_direction, service, deployed_after, deployed_before. Call harness_describe for filters available on a specific resource_type.
project_idNoProject identifier (overrides default)
search_termNoFilter results by name or keyword
resource_typeNoResource type to list. Auto-detected from url.
resource_scopeNoScope to query. Use account for account-level resources and to omit org/project defaults; org injects only org; project injects org+project. Auto-detected from url.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoCurrent page number (0-indexed) when provided by the API
itemsNoArray of resource objects or primitive values when the API returns a canonical list
totalNoTotal number of matching resources when provided by the API
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description mentions filtering, pagination, and URL-based scope extraction, which adds some behavioral context beyond the readOnlyHint annotation. However, it doesn't disclose limitations such as per-resource max page sizes or how auto-scope extraction behaves when no URL is provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

At two sentences, the description is concise and front-loaded with the core action. It avoids verbosity but is perhaps too sparse given the tool's complexity, though it remains efficiently structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 11 parameters, including enums and nested objects, the two-sentence description is insufficient. It doesn't explain how the tool fits into the overall workflow, what kinds of resources can be listed, or how to use the URL vs explicit scope parameters. The output schema exists but doesn't provide usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides detailed descriptions for all 11 parameters, covering 100% of them. The description's mention of URL scope extraction is redundant with the schema's url parameter description, so it adds no new meaning beyond what the schema already explains.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists Harness resources with filtering and pagination, which is a specific verb+resource. It doesn't explicitly differentiate from sibling tools like harness_search, but the core action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives like harness_search or harness_get. It mentions URL scope extraction but doesn't explain when to prefer this tool over other listing or searching tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/harness/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server