mcp-server
IntegrationCloud & infraInspect AgentMark traces and drive AgentMark Cloud: apps, experiments, metrics, deployments.
This server has no hosted endpoint yet, so ahel can't serve it. You can still add it. It stays paused until ahel can serve it.
One link, every agent. Your own credentials, stored once.
Tools it gives your agents (79)
| Tool | What it does |
|---|---|
| service_health | Service health — Check if the gateway service is running. Returns healthy if all required environment variables are configured. |
| ingestion_health | Ingestion health — Check the health of the trace ingestion pipeline and its dependencies. |
| files_health | Files health — Check the health of the files service and its dependencies. |
| get_capabilities | Get capabilities — Returns a map of available API endpoints for the current target (cloud or local). |
| get_pricing | Get LLM pricing — Returns per-model pricing for cost calculation. Response is a dynamic map keyed by model ID (e.g. `gpt-5`, `claude-opus-4-6`). |
| get_template | Get template — Retrieve a prompt template by its file path. Templates must have a `.mdx` or `.jsonl` extension. |
| list_traces | List traces — Retrieve a paginated list of traces. Supports filtering by status, user, model, and date range. |
| ingest_traces | Ingest traces — Ingest trace data in [OTLP (OpenTelemetry Protocol)](https://opentelemetry.io/docs/specs/otlp/) format. Traces are buffered in a queue and processed asynchronously. Supports... |
| search_traces | Search traces — Search traces with structured JSON filters — the programmatic form of the `filter` string DSL on `GET /v1/traces`. |
| get_trace | Get trace — Retrieve a specific trace by ID, including all its spans. Pass `?fields=graph` to include agent-workflow DAG nodes in the `graph` field of the response. |
| list_spans | List spans — Query spans across all traces. Supports filtering by type, status, model, name, and duration range. |
| get_blob | Fetch an offloaded span field blob — Returns the full content of a span field payload (input/output/...) that was offloaded to object storage at ingest. |
| search_spans | Search spans — Search spans with structured JSON filters — the programmatic form of the `filter` string DSL on `GET /v1/spans`. |
| get_span | Get span — Fetch a single span by its globally-unique span_id, without needing its trace_id. Returns the full span: metadata plus its input/output payload (the span analog of GET /v1/traces/:traceId). |
| list_trace_spans | List spans for a trace — Returns every span belonging to the given trace, ordered by start time. |
| get_span_detail | Get span I/O detail — Returns the full input/output payload for a specific span, plus parsed output objects, tool calls, and the span’s custom metadata (reserved internal namespaces excluded). |
| list_sessions | List sessions — Retrieve a paginated list of sessions. Sessions group related traces together for multi-turn conversations, workflows, and batch processing. |
| get_score_aggregations | Get score aggregations — Returns aggregated statistics for scores grouped by name. |
| get_score_names | Get score names — Returns a list of distinct score names used in your application. Useful for building filter dropdowns and discovering available score types. |
| list_scores | List scores — Returns a paginated list of scores for the authenticated application. Supports filtering by resource, name, source, and date range. |
| create_score | Create score — Create a score record for a span or trace. Scores are used to track quality metrics, evaluation results, and human feedback. <Note>This endpoint was consolidated from `/v1/score`... |
| search_scores | Search scores — Search scores with structured JSON filters. `filters` is an AND-list of predicates (`{field, operator, value}`) and one-level OR-groups (`{or: [...]}`) over the score fields: name... |
| get_score | Get score — Retrieve a single score record by ID. Returns the full score object including its value, label, reason, and source. |
| delete_score | Delete score — Delete a score record by ID. |
| create_scores_batch | Create scores (batch) — Create up to 1000 scores in a single request. Each item is validated independently and the response always contains a per-item results array. Status codes: - `201 Created`... |
| get_filter_schema | Get filter schema — Machine-readable description of the filterable surface for `POST /v1/traces/search`, `POST /v1/spans/search`, `POST /v1/scores/search`, and the `filter` string DSL on the GET... |
| get_metrics | Get metrics — Retrieve aggregated analytics metrics for your application. Returns a summary and an hourly time series for trace volume, latency, cost, token usage, and error rates. **Cloud only.**... |
| list_experiments | List experiments — Retrieve a paginated list of experiments (dataset runs). Each experiment is a group of traces that share a `DatasetRunId`, typically produced when a prompt is evaluated against... |
| get_experiment_baseline | Get baseline scores — Return per-(row × scorer) scores from the baseline run matching `commit_sha` (a content-addressed git tree hash), optionally narrowed by `dataset_path`. |
| get_experiment | Get experiment — Retrieve a specific experiment by ID, including its per-item details (trace IDs, inputs/outputs, per-item cost/latency/tokens, and any scores attached to each trace). |
| list_datasets | List datasets — Returns a paginated list of datasets for your application with per-dataset metadata (`row_count`, `created_at`). `?name=X` does an **exact match** on the dataset's leaf name (the... |
| append_dataset_row | Append dataset row — Appends a single row to the specified dataset. The `datasetName` parameter is the dataset path without the `.jsonl` extension, URL-encoded. For example, to append to... |
| import_dataset_rows_from_traces | Import dataset rows from traces — Transforms one or more traces into canonical dataset rows and appends them to the specified dataset. |
| import_dataset_rows_from_spans | Import dataset rows from spans — Transforms one or more spans into canonical dataset rows and appends them to the specified dataset. |
| get_config | Get config — Returns the effective project configuration synced from `agentmark.json` for the authenticated application, plus the current synced commit SHA when available. |
| list_prompts | List or look up prompts — List prompt files. With `?name=X`, filters to prompts whose frontmatter `name` matches — used by the trace drawer to map a span's `prompt_name` back to a file path. |
| list_annotation_queues | List annotation queues — Returns every annotation queue for the authenticated application, with per-queue progress counters (pending / in_progress / completed / skipped / total). When... |
| create_annotation_queue | Create annotation queue — Creates a new queue for collecting human review on traces, spans, or sessions. |
| get_annotation_queue | Get annotation queue — Returns metadata for a single queue by ID. |
| update_annotation_queue | Update annotation queue — Updates mutable queue metadata (`name`, `description`, `status`, `instructions`, `reviewers_required`, `score_config_names`). Fields not provided are left unchanged. |
| delete_annotation_queue | Delete annotation queue — Deletes a queue. Cascades to its items and reviewer records. |
| list_annotation_queue_items | List queue items — Returns every item enqueued for review, in the order they were added. |
| add_annotation_queue_items | Add items to queue — Adds one or more traces/spans/sessions to the queue for review. Duplicate `(queue_id, resource_id)` pairs are ignored silently. |
| get_annotation_queue_item | Get queue item — Returns a single queue item by ID. |
| update_annotation_queue_item | Update queue item — Updates item status or assigned reviewer. Setting status to `completed` auto-records `completed_by` / `completed_at`. |
| delete_annotation_queue_item | Delete queue item — Removes an item from a queue. Cascades to reviewer records. |
| submit_annotation_queue_review | Submit review — Submit a review (`completed` or `skipped`) on behalf of the authenticated user. |
| list_api_keys | List API keys — Returns API keys for the authenticated tenant. Plaintext is never returned on this endpoint — record it at creation time. |
| create_api_key | Create API key — Creates a new API key. The plaintext key is returned EXACTLY ONCE in `data.plaintext_key` — record it immediately. Subsequent reads expose only metadata. |
| revoke_api_key | Revoke API key — Revokes the API key and removes its local metadata row. Note: a brief revocation lag may occur — the gateway caches verified credentials for a short TTL, so a freshly-revoked key... |
| list_score_configs | List score configs — Returns the score configs declared in the application's `agentmark.json` (synced on deploy). Read-only — to add or modify a config, edit `agentmark.json` and redeploy. |
| get_score_config | Get score config — Returns a single score config by name. The name is the object key in `agentmark.json`'s `scores` map. Returns 404 if no config with that name is declared. |
| list_deployments | List deployments — Returns a paginated list of deployments for the authenticated application, newest first. |
| get_deployment | Get deployment — Returns a single deployment by id. The response includes status (`deployment_status`, `files_status`, `code_status`), commit metadata, timing, and any failure reason — sufficient to... |
| list_environments | List environments — Returns environments for the authenticated application, default env first. |
| create_environment | Create environment — Creates a new environment in the current app. The env starts in the no-pin state — promote (POST `/v1/environments/{id}/promote`) is the only path to pin a version. |
| get_environment | Get environment — Returns a single environment by id. Includes `cascade_preview` (counts of api_key / alert / deployment / template_snapshot rows that would be deleted on env delete — see FR-090)... |
| delete_environment | Delete environment — Hard-deletes a non-default environment after a typed-name confirmation. |
| promote_environment | Promote to environment — Promotes the source environment's current content + code into this environment. |
| rollback_environment | Roll back an environment — Rolls this environment back to a prior pinned version (FR-018..FR-023). |
Signals
- Weekly downloads
- 45
- Tools captured
- 79
Advanced
- Delivery
- mcp-server MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
- Catalog kind
- mcp-server
- Gateway key
io-github-agentmark-ai-mcp-server- Source
- github.com/agentmark-ai/agentmark