Artificial Intelligence
OpenPipe
Connect OpenPipe once and hand every teammate a governed MCP endpoint with 23 tools ready to call from Claude, ChatGPT, Cursor, or any MCP client, inside the same permissions they already have, with every call checked and logged.
Automations & dashboards
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards ship on the Black plan.
Automations
Put OpenPipe work on a schedule.
A trigger starts a sequence of steps: call a OpenPipe tool, transform the result, branch, wait, and ask a person when it matters.
OpenPipe digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch models
OpenPipe
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
OpenPipe
Queued
Collections and dashboards
Report on OpenPipe without asking.
Collections hold your own data, written by an automation and read by a dashboard that refreshes on a schedule.
OpenPipe health
Refreshed 4 minutes ago · every 15 minutes · from the models collection
Models
1,284 ↓ 12%
Datasets
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Models created
Last 14 days
By workspace
Share of activity
Engineering 34%
Product 27%
Support 21%
Sales 18%
AI tools
OpenPipe tools for your AI agents
23 tools are ready to call through Elaichi's MCP endpoint the moment you connect OpenPipe, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
create_a_openpipe_check_cach
Check a cached prompt request in OpenPipe. Returns: respPayload. Deprecated: OpenPipe no longer supports prompt caching. Required: requestedAt.
create_a_openpipe_chat_completion
Create a chat completion in OpenPipe. Returns the generated completion object including id, object, created, model, choices, and usage. Required: messages, model.
create_a_openpipe_report
Record a request log from an OpenAI model in OpenPipe. Returns: status.
create_a_openpipe_report_anthropic
Record a request log from an Anthropic model call in OpenPipe. Returns: status. Optional fields include statusCode, errorMessage, metadata, and tags.
create_a_openpipe_logs_update_tag
Update tags on OpenPipe log entries matching the given filters. Returns: matchedLogs. Deprecated: use /logs/update-metadata instead. Required: filters, tags.
create_a_openpipe_logs_update_metadata
Update tags metadata for logged OpenPipe calls matching the provided filters. Returns: matchedLogs. Required: filters, metadata.
list_all_openpipe_local_testing_only_get_latest_logged_calls
Get the latest logged call from OpenPipe. Returns the call object with createdAt, cacheHit, statusCode, reqPayload, respPayload, tags, and metadata. Local testing only.
create_a_openpipe_criteria_judge
Judge a completion against an OpenPipe criterion. Returns: score, explanation, usage. Required: criterion_id, output.
list_all_openpipe_datasets
List datasets in an OpenPipe project. Returns dataset objects with id, name, created, updated, dataset_entry_count, and fine_tune_count.
create_a_openpipe_dataset
Create a new dataset in OpenPipe. Returns the created dataset including id, name, created, updated, dataset_entry_count, and fine_tune_count. Required: name.
delete_a_openpipe_dataset_by_id
Delete a dataset in OpenPipe by id. Returns the deletion status with id, object, and deleted. Required: id.
create_a_openpipe_dataset_entry
Create new dataset entries in OpenPipe. Returns the creation summary including object, entries_created, and errors (with entry_index and message). Max 100 entries per request. Required: dataset_id, entries.
list_all_openpipe_models
List all models in an OpenPipe project. Returns models with id, name, openpipe status, contextWindow, and pricing.
create_a_openpipe_model
Train a new model in OpenPipe. Returns the created model including id, name, openpipe status, and pricing. Required: datasetId, slug, trainingConfig.
delete_a_openpipe_model_by_id
Delete an OpenPipe model by its slug. Returns: id, object, deleted. Required: id.
get_single_openpipe_model_by_id
Get a single OpenPipe model by id. Returns the model object including id, name, openpipe status, contextWindow, and pricing. Required: id.
create_a_openpipe_dataset_create
Create a new dataset in openpipe. Returns: datasetId. Deprecated; prefer the `/datasets` endpoint. Required: name.
create_a_openpipe_dataset_delete
Delete an OpenPipe dataset by its datasetId. Returns: datasetId. Deprecated endpoint; use the `/datasets/{dataset}` endpoint instead. Required: datasetId.
list_all_openpipe_dataset_lists
List OpenPipe dataset lists via the deprecated /unstable/dataset/list endpoint. Returns an array of dataset objects with id, name, createdAt, updatedAt, datasetEntryCount, and fineTuneCount. Prefer the /datasets endpoint instead.
create_a_openpipe_dataset_entry_create
Create dataset entries in OpenPipe. Returns: createdEntries, errors. Deprecated: use `/datasets/{dataset}/entries` instead. Required: datasetId, entries.
create_a_openpipe_finetune_create
Create a fine-tune job in OpenPipe. Returns the new fine-tune job's id. Deprecated. Required: datasetId, slug, baseModel.
list_all_openpipe_finetune_gets
Get a fine-tuned model in openpipe by id or slug. Returns: id, status, slug, baseModel, errorMessage, datasetId, createdAt. Deprecated: use the `/models/{model}` endpoint instead.
create_a_openpipe_finetune_delete
Delete an openpipe fine-tuned model by id or slug. Returns: deleted. Deprecated: use the `/models/{model}` endpoint instead.
No tools match your search.
How it works
From OpenPipe account to governed MCP endpoint
Connect
Link a OpenPipe account through Elaichi's hosted connect flow. Credentials are vaulted, so nobody, including the AI, ever sees them.
Compose
The connection becomes a toolbox instantly. Curate which OpenPipe tools are exposed, rename them, or freeze arguments.
Authorize
Point Claude, ChatGPT, Cursor, or any MCP client at the one Elaichi endpoint and sign in with OAuth, governed by roles, restrictions, and audit logs.
Put your agents to work in the tools you already use
Start a 14-day Gold trial. Connect a product, curate a toolbox, and paste a governed MCP endpoint into Claude, ChatGPT, or Cursor in minutes.