MCP App Store
by KeenEthics

Overview

3Min API turns a plain-language description into a working REST API endpoint — no backend code to write or host. Describe what you want to collect (inquiries, orders, signups) and an endpoint goes live. Define a JSON schema if you want field validation, or skip it to accept any payload. Every endpoint comes with full CRUD operations, separate sandbox and production environments, searchable call logs, and usage statistics. New records reach your own system by webhook, or by polling when your server can't be reached from the internet. With Tasks, you can also hand a job to a worker you run on your own server — such as an AI agent — and check the result right in the chat. 3Min API delivers the job and records its status; the work itself runs on your server. With this connector you can: • Create, update, and deploy endpoints — one sentence is enough, and each new endpoint is automatically verified with a test call • Send real requests to your own endpoint (create, read, update, delete) to confirm it works before going live • Search everything you have received by keyword across the entire payload, or look up a single record • Start jobs on your workers, check their progress and results, and cancel them • Track monthly and daily usage with success rates and response times • Issue scoped access keys for partners and control exactly which operations each one may perform Every action is scoped to your own account; other users' resources are never reachable. Sign-in uses OAuth, so no API keys are exchanged in conversation, and responses mask sensitive values such as access keys and collaborator email addresses — full values remain available only on the web dashboard. Webhook authentication headers and task worker credentials are likewise set only on the dashboard and are never requested in conversation. Deleting an endpoint, registering task workers, changing plans, and billing are handled on the web dashboard, not through this connector.

Tools

api_call

ChatGPT
Call your API endpoint via the Gateway using the default collaboration key. Use help(topic: "api") for error codes. Workflow: 1. endpoints(action: "get") — check field definitions and API key 2. api_call(environment: "sandbox") — test with sandbox 3. logs — verify the result 4. collaborators — create keys and invite partners 5. endpoints(action: "deploy") — deploy to production (when all testing is done) Only do what the user asks. After completing a step, briefly list what else is available and let the user choose. - POST: Create record (async, 202). Requires body. - GET: Read record (sync, 200). Requires record_id. - PUT: Replace record (async, 202). Requires record_id + body. - DELETE: Delete record (async, 202). Requires record_id. Note: To search records by keyword, use the logs tool (search_text), not api_call GET. GET only retrieves a single record by record_id. Supported: POST, GET, PUT, DELETE via default collaboration key. Not supported (web only): call with non-default collaboration key.

archives

ChatGPT
Bulk download of archived API payloads. Only needed for bulk export — for individual records, use logs with fetch_archived=true instead. Production records older than the retention period have payloads archived as gzip-compressed JSONL files. Sandbox records are not archived. Use help(topic: "archives") for file format and error codes. Workflow: 1. list — browse archived files by date range (max 3 months, paginated) 2. download — get a temporary download URL (expires in 5 minutes) 3. Download the file, decompress (gzip), and parse line-by-line as JSON 4. If download fails in your environment, provide the URL to the user for manual download Supported: list archive files, get download URL. Not supported (web only): visual archive browser.

collaboration_key_create

ChatGPT
Use this when the user wants someone outside — a partner, a client, another team — to call an endpoint with their own API key, so that one party's access can be narrowed or withdrawn without touching anyone else. Not for the user's own calls: every endpoint already has a default API key, and most endpoints never need another. Examples: "Give our fulfilment partner a key for orders", "Set up read-only access for the client" Creates a collaboration key holding two API keys, sandbox and production, both switched on. allowed_operations — all four when omitted — is set for both environments, so on an endpoint already deployed the new key can call production straight away with those operations. key_name is unique per endpoint, so the same request sent again is rejected rather than creating a second key. Key values are masked in the response; the full values are on the endpoint's dashboard page. Deleting a key, switching one off, regenerating it and renaming it are dashboard-only. help(topic: "collaborators") has the permission rules and error codes — read it when a call is rejected, not to make one.

collaboration_key_list

ChatGPT
Use this when the user asks who can call an endpoint or what a partner is allowed to do. Not for the full key values — those are shown only on the endpoint's dashboard page. Examples: "Who has access to the orders endpoint?", "What can our fulfilment partner do on production?" Read-only: returns the endpoint's collaboration keys, newest first, ten per page — each with its name and description, whether its sandbox and production keys are switched on, and the operations allowed in each environment. Key values are masked. The row with is_default true is the endpoint's own default key; the others were made for people outside.

collaboration_key_set_permissions

ChatGPT
Use this when the user wants to change what a partner's collaboration key may do in one environment — allow or stop creates, reads, updates or deletes. Not for the endpoint's own default key, whose permissions cannot be changed, nor for switching a key off, which is dashboard-only. Examples: "Stop that partner from deleting records", "Let the client only read on production" Replaces the key's allowed operations for the environment given with the list sent — nothing is added to what was there. The change applies from the key's next call, so an operation left out is refused from then on. Deploy copies each key's sandbox set over production, so a set narrowed only on production is widened again by the next deploy. help(topic: "collaborators") has the permission rules and error codes — read it when a call is rejected, not to make one.

collaborator_invite

ChatGPT
Use this when the user wants a specific person to get access to an endpoint through a collaboration key — the person receives an email, signs up, and accepts on the dashboard. Not for revoking an invitation — that is dashboard-only. Examples: "Invite dana@example.com to the orders endpoint", "Send our partner's developer an invite" Sends an invitation email to the address given, for the collaboration key given; the invitation expires after seven days. The address must be the full one — a masked value is rejected — and cannot be the user's own. Inviting an address whose invitation is still pending sends the email again and restarts the seven days rather than creating a second invitation, unless the key is already at its limit of active invitations; an address that has already accepted is rejected. help(topic: "collaborators") has the invitation limits and error codes — read it when a call is rejected, not to make one.

collaborator_invite_list

ChatGPT
Use this when the user asks who has been invited to an endpoint or whether an invitation was accepted. Not for revoking an invitation — that is dashboard-only. Examples: "Did Dana accept the invite?", "Who have I invited to orders?" Read-only: returns the endpoint's pending and accepted invitations, newest first, ten per page — each with its collaboration key, its status, and when it was sent, accepted and due to expire. Invitee email addresses are masked, so sending an invitation again needs the full address from the user.

collaborators

ChatGPT
Manage collaboration keys and invitations for your endpoints. Use help(topic: "collaborators") for permission rules and error codes. Workflow: 1. list_keys — view existing collaboration keys 2. create_key — create a key for a new partner 3. update_permissions — set CRUD permissions per environment 4. invite — send email invitation to a collaborator 5. list_invitations — check invitation status Only do what the user asks. After completing a step, briefly list what else is available and let the user choose. Supported: list keys, create key, update permissions, list invitations, invite by email. Not supported (web only): delete/deactivate key, regenerate API key, revoke invitation, edit key name/description.

endpoint_create

ChatGPT
Use this when the user wants an HTTP endpoint that receives JSON and stores each record — a contact form, an order feed, a partner's system. Not for changing an endpoint that already exists — that is endpoint_update. Examples: "Somewhere to collect enquiries from my site", "An API my partner can send orders to" Creates the endpoint with a default API key and returns its URL, then runs one sandbox test call with a sample payload, in testCall. That call counts toward usage like any other, stores one sample record, and is delivered to webhook_url when one is set for sandbox. field_definitions is optional: omit it and any JSON is accepted; each declared field becomes required on later calls. endpoint_name is unique per user, so the same request sent again is rejected rather than creating a second endpoint. The new endpoint is live in sandbox only; production rejects its calls until it is deployed. Records reach the user's system two ways: pushed to a webhook_url, or pulled by their client from the poll URL. webhook_url is settable here; its auth header is not and lives on the dashboard. help(topic: "endpoints") has the field name rules and error codes; help(topic: "webhooks") and help(topic: "polling") have the two receiving contracts — read them when a call is rejected or that side is being built, not to make a call.

endpoint_deploy

ChatGPT
Use this when the user wants an endpoint live in production. Not for editing its fields or webhook — that is endpoint_update. Examples: "Put this live", "Deploy the orders endpoint", "My partner is ready to send real data" Deploy copies the endpoint's sandbox configuration — its field definitions and each collaboration key's allowed operations — to production and switches production on. Production then keeps that configuration fixed while sandbox changes, until the next deploy. Webhook settings are not copied. Pending deployment requests from collaborators who are still invited are marked deployed and each of those requesters is emailed; requests from collaborators no longer invited are cancelled. Sandbox and production share one URL and differ only in the key prefix — tm_test_ or tm_live_ — so a call lands wherever its key points, and no success response says which. Before the first deploy, production rejects every call.

endpoint_get

ChatGPT
Use this when the user asks how one endpoint is set up — its fields, its API keys, its webhook, its URLs. Not for the records it has received — that is record_list or record_get. Examples: "What fields does the orders endpoint take?", "Is a webhook set on my contact form?", "What's the polling URL?" Read-only: returns the sandbox and production field definitions, the collaboration keys with their API keys masked, each environment's webhook URL, and the URLs the user's own client calls — apiUrl, pollUrl and searchUrl. Webhook auth header values are not shown; whether one is saved is.

endpoint_list

ChatGPT
Use this when the user wants to see which endpoints they have, or asks whether anything is wrong with them. Not for one endpoint's fields, keys or webhook — that is endpoint_get. Examples: "What endpoints do I have?", "Is anything wrong with my APIs?" Read-only: returns the user's endpoints, newest first, ten per page — each with its name, URL, whether sandbox and production are switched on, and when it was first deployed. The first page also reports what the owner has not been told: an endpoint whose calls keep being rejected, a deleted endpoint that is still being called, this month's calls nearing the limit, and an endpoint due for automatic deletion.

endpoint_update

ChatGPT
Use this when the user wants to change an existing endpoint — rename it, edit its description, change its fields, or set or clear its webhook URL. Not for deleting an endpoint or switching it on or off — those are dashboard-only. Examples: "Add a phone field to orders", "Send the contact form to https://example.com/hook", "Stop the webhook on orders" Changes only the fields given. field_definitions replaces the whole sandbox field list and each declared field becomes required on later sandbox calls; production keeps the fields it was last deployed with until the next deploy, and an endpoint never deployed has none — production rejects its calls. webhook_url applies to the environment given, sandbox when omitted. The webhook's auth header is not settable here and lives on the dashboard. A header already saved there keeps being sent when the URL changes, but clearing webhook_url clears that header too, and only the dashboard can set it again. help(topic: "endpoints") has the field name rules and error codes; help(topic: "webhooks") has the receiving contract — read them when a call is rejected or the receiver is being built, not to make a call.

endpoints

ChatGPT
Manage API endpoints: list, view, create, update, and deploy to production. Use help(topic: "endpoints") for field rules and error codes. Webhook vs Notification (different purposes): - Webhook: forwards full API call data to your server URL on every API call. For data processing. - Notification: sends short alerts to Discord/Slack/Telegram for system events only (webhook failure, usage warning, etc.). NOT triggered on API calls. Workflow: 1. create — new endpoint 2. api_call — test in sandbox 3. logs — verify results 4. collaborators — create keys and invite partners 5. deploy — push sandbox config to production (when all testing is done) Only do what the user asks. After completing a step, briefly list what else is available and let the user choose. Supported: list, get, create, update, deploy, webhook/notification config. Not supported (web only): delete endpoint, toggle active/inactive.

help

ChatGPT
3Min API service guide. Returns detailed reference by topic. When to use: - Before using any tool for the first time - When encountering errors (topic: "troubleshooting") - To understand field rules, error codes, or business constraints Topics: overview, pricing, endpoints, collaborators, webhooks, api, troubleshooting, logs, subscription, stats, archives, mcp

logs

ChatGPT
Search and retrieve API call logs. This is the tool for finding records by keyword or verifying API call results. Two modes: record lookup (by record_id) or text search (by search_text with date range). Use help(topic: "logs") for error codes and search constraints. When to use this tool: - "Show me orders containing John" → text search (search_text: "John", start_date, end_date) - "Check if my test call went through" → record lookup (record_id from api_call response) Workflow: 1. Record lookup — exact record_id, returns full payload. If payload is null, it has been archived — retry with fetch_archived=true to retrieve it. 2. Text search — partial match (ILIKE) on searchable fields. Min 3 chars, max 31-day range, paginated (10 per page). Note: For bulk export of archived data, use the archives tool instead. Supported: single record lookup, text search with date range, archived payload retrieval. Not supported (web only): visual log browser, CSV export, client filter.

record_create

ChatGPT
Use this when the user wants to store a new record in one of their endpoints — a test submission or real data. Not for changing or removing a record that already exists. Examples: "Send a test order through", "Add this lead to the contacts endpoint", "Save today's reading in sandbox" Runs with the endpoint's own default API key; a collaboration key cannot be used here. Accepted asynchronously: the response is 202 with the new record's id, and the record is written a few seconds later, so it can be read back about 5 seconds on. If the endpoint has a webhook for that environment, the record is also delivered to that URL. Each call costs one call against the monthly quota. Sending the same body again stores a second record and delivers it again — after a 202 the id is already assigned. help(topic: "api") has the error codes — read it when a call is rejected, not to make one.

record_delete

ChatGPT
Use this when the user wants a record removed from an endpoint. Not for deleting the endpoint itself, which is dashboard-only. Examples: "Delete that test order", "Remove the duplicate contact from production" Removes the record with the id given; it cannot be restored. Accepted asynchronously: the response is 202 and the record is gone a few seconds later. If the endpoint has a webhook for that environment, the deletion is delivered to that URL. Each call costs one call against the monthly quota. help(topic: "api") has the error codes — read it when a call is rejected, not to make one.

record_get

ChatGPT
Use this when the user wants one record in full by its id — to confirm a write landed or to see exactly what was stored. Not for finding out why a record failed or whether its webhook fired: error details and delivery state are not part of a record. Examples: "Did that order come through?", "Show me what record 0192f3a1 holds" Read-only: returns the record with its payload as stored in the environment given. A record accepted a few seconds ago may not be readable yet, and a sandbox record is never found in production. Each read costs one call against the monthly quota.

record_list

ChatGPT
Use this when the user wants to see the most recent records of an endpoint. Not for keeping up with new records over time: the list is newest first and cannot say "since when", so repeating it fetches the same page again and pays for records already seen. Examples: "Show me the last few submissions", "What's in the orders endpoint right now?" Read-only: returns a page of whole records with their payloads, newest first — 10 by default, up to 30 — and a cursor for the next page when there is one. Each page costs one call against the monthly quota.

record_poll

ChatGPT
Use this when the user wants what has arrived since a point in time, or is building something that keeps up with new records. Not for showing the latest records once: this reads forward from a point, oldest first. Examples: "Has anything new come in since this morning?", "Set up a sync that pulls new orders every few minutes" Read-only: returns records oldest first, up to 100 per call, after since on the first poll and after the cursor from the previous response on every poll after it — so it is the read that can say "since when", and a client that passes the cursor back never gets a record twice. Every poll costs one call against the monthly quota, including one that comes back empty. help(topic: "polling") has the polling contract — read it when a polling loop is being built, not to make one call.

record_update

ChatGPT
Use this when the user wants to change a record that already exists. Not for adding a new record. Examples: "Mark that order as shipped", "Fix the email on the last contact" Replaces the record with body as a whole — every field left out of body is erased — so changing one field means reading the record first and sending it back with that change applied. Accepted asynchronously: the response is 202 and the change is written a few seconds later. If the endpoint has a webhook for that environment, the updated record is delivered to that URL. Each call costs one call against the monthly quota, and sending it again delivers it again. help(topic: "api") has the error codes — read it when a call is rejected, not to make one.

stats

ChatGPT
Get API usage statistics: monthly summary and daily CRUD breakdown with success/failure counts and average response time. Use help(topic: "stats") for field details. Workflow: 1. stats — check current month usage 2. subscription — compare usage against plan limit, consider upgrade if needed Note: Statistics may have slight delays. Response time excludes Read operations. Supported: monthly summary, daily breakdown, historical months. Not supported (web only): visual charts, date range comparison.

subscription

ChatGPT
Get current subscription plan, usage, and billing info. No parameters needed. Use help(topic: "subscription") for field details. Workflow: 1. subscription — check usage percentage and plan limits 2. If usage is high, review available_plans for upgrade options 3. Plan changes are made on the web dashboard (manage_url in response) Supported: view current plan, usage, billing period, available plans. Not supported (web only): change plan, cancel, reactivate, payment management.

task_cancel

ChatGPT
Use this when the user wants to stop one or more tasks that have not finished. Not for stopping work already underway: a worker that already received the task may still carry it out. Examples: "Cancel that order", "Stop all the imports I just started" Takes up to 100 task ids and returns a result for each: cancelled, already_terminal (with the final status), or not_found. Some ids being cancelled while others are not is a normal outcome. Cancelling marks the task cancelled and stops any further delivery. A worker already running the job finds out late — a public worker when its next status report comes back 409, a local worker when the 3Min API CLI next fetches from 3Min API. Completed, failed and cancelled tasks never change status.

task_create

ChatGPT
Use this when the user wants a job handed to one of their registered workers. Not for storing data — that is an endpoint and api_call. A task is work given to a server the user runs. Examples: "Ask the inventory worker to restock SKU 1042", "Run the monthly report on my reporting worker now" 3Min API does not run the job: it delivers the JSON input to the worker as a signed POST and returns a task id with status "working". The worker then sets the status through the status report API — progress messages while working, then completed with a result or failed with an error. Each delivery carries its callback_url, and the callback key it authenticates with is on that worker's own page — dashboard, Tasks, Workers, the worker, Callback key. It is never returned here. A task not reported completed or failed within 24 hours is marked failed, as is one that could not be delivered. The same worker and input sent again within about 2 to 4 minutes returns the existing task unless it failed. input is limited to 100 KB. How the worker receives and reports, and how long records last: help(topic: "tasks").

task_get

ChatGPT
Use this when a specific task id is at hand and the user wants that task's current status or its outcome. Not for waiting on a task: a working task returns the same response until the worker reports, so calling again in a loop costs a call and changes nothing. Examples: "Is it done yet?", "What did the worker send back?" Returns the full task in any status: status (working, completed, failed or cancelled), status_message, delivery, repeat (settings and run counts, for a repeating task), and — once finished — the result or error, passed through unmodified, up to about 100 KB. delivery splits "working" in two: "pending" means the worker has not received the task yet — a public worker's URL has not accepted it, or the 3Min API CLI on the user's PC has not fetched it for a local worker — and "delivered" means the worker has it. These values come from the worker's calls to the status report API (for a local worker, the CLI makes them) — but a failed task does not always mean the worker reported one. 3Min API itself sets failed, with its own error, when delivery never succeeded or 24 hours passed without a final report (for a repeating task, without a run report), and cancelled on cancellation. A task id from another account, or one past retention, is reported as not found. Telling those apart, and what to check for each: help(topic: "tasks").

task_list

ChatGPT
Use this when the user asks about their tasks without a specific task id at hand — what is running, what has finished, or what happened to something started earlier, including in a previous conversation. Not for a task's result or error: rows carry neither, and task_get is where they are. Examples: "How did that order I sent go?", "Show my recent tasks", "Is the import still running?" Returns a summary of every task within retention — all statuses, most recently updated first, 25 per page (up to 100) with keyset pagination. Each row has the task id, worker name, status, status_message, delivery and timestamps. status and status_message are set by the worker through the status report API (for a local worker, the CLI calls it), or by 3Min API when delivery fails, 24 hours pass without a report, or the task is cancelled; for a failed task status_message holds the reason. delivery is "pending" until the worker has received the task and "delivered" after, so a working task that is still pending has not reached its worker yet.

task_result_describe

ChatGPT
Use this when the paths of a saved task result are needed before computing from it — which fields it has, their types and ranges — or when a worker's results may have changed shape over time. Not for the values themselves: this returns a summary of the structure, not the result. Examples: "What fields does that big result have?", "Did the orders worker's output change this week?" This tool creates a task for the built-in results reader on the user's PC: it returns a task id with status "working", and the reader reports back the summary, which task_get returns. The reader is a local worker that the 3Min API CLI registers, and it answers only while that CLI is running there. 3Min API picks the PC by host when given, otherwise the PC of the task_id or worker given, otherwise the only PC that has a reader. With task_id it lists that result's paths, each with its types and count, number ranges, array lengths and short text values, up to 200 paths; run_no picks one run of a repeating task, the latest without it. With worker, optionally since, it groups that worker's results by shape and lists the paths each shape has or lacks compared with the latest. Each call is a new task: it costs calls like any task — at least 4, counting task_get — and shows in task_list. The same input sent again within about 2 to 4 minutes returns the existing task. How the paths are used: help(topic: "tasks"), "Reading a large result".

task_result_query

ChatGPT
Use this when the user wants an answer computed from task results saved on their PC — a total, an average, the rows that match — rather than the raw results. Not for a result that task_get already returned in full: its result field holds it. Examples: "What was the average price over the last 20 runs?", "Total the amounts in that large export" This tool creates a task for the built-in results reader on the user's PC: it returns a task id with status "working", and the reader reports back the answer, which task_get returns. The reader is a local worker that the 3Min API CLI registers, and it answers only while that CLI is running there. 3Min API picks the PC by host when given, otherwise the PC of the task_id, task_ids or worker given — all on one PC, since a reader sees only its own — otherwise the only PC that has a reader. sql is read-only SQL over one view, results: one row per saved result (per run, for a repeating task) with task_id, run_no, worker, created_at, status, bytes, shape_hash and payload, the result JSON. Only the scope given is visible — worker, task_id, task_ids, since, at least one, combined with AND — and writes or other tables are refused. A JSON path the SQL names that no result in the scope has reads as NULL and is listed in missing_paths. Each call is a new task: it costs calls like any task — at least 4, counting task_get — and shows in task_list. The same input sent again within about 2 to 4 minutes returns the existing task. Which paths a result has, and how to compute over them: help(topic: "tasks"), "Reading a large result".

task_result_read

ChatGPT
Use this when the user needs part of a saved task result as it is — the items or text themselves, not a figure computed from them. Not for totals, counts or searches over a result: task_result_query computes those on the PC and sends back only the answer. Examples: "Show me the first 50 items of that export", "Give me the raw text of run 3" This tool creates a task for the built-in results reader on the user's PC: it returns a task id with status "working", and the reader reports back the piece, which task_get returns. The reader is a local worker that the 3Min API CLI registers, and it answers only while that CLI is running there. 3Min API picks the PC by host when given, otherwise the PC of the task_id, otherwise the only PC that has a reader. It returns up to about 90 KB of the value at path — $ by default, the whole result — starting at offset: array elements, object keys or text characters, with total and next (null at the end). run_no picks one run of a repeating task, the latest without it. Each call is a new task: it costs calls like any task — at least 4, counting task_get — and shows in task_list, and each piece waits until the CLI fetches it. The same input sent again within about 2 to 4 minutes returns the existing task. Reading in pieces: help(topic: "tasks"), "Reading a large result".

wordpress_plugin

ChatGPT
Use this when the user mentions WordPress, a blog or a WP site — or picks WordPress as where their API will be called from. Not for writing the snippet itself: this returns the prompt to generate it from, and the generating is yours. Examples: "Put this form on my WordPress site", "Show submissions on a page of my blog", "How do I use this with WordPress?" The 3Min API Connector plugin drops an endpoint into any post or page through a [3minapi] shortcode. Call with no section for an index and the code-generation workflow; section "overview" for the plugin and its URL, "usage" for the user guide, and "ai_codegen_prompt" for the system prompt that generates snippet code — a verbatim mirror of the plugin's own "Copy AI prompt" output, so generated code follows the same rules. Snippets come in three shapes, set by method: get_record, get_list and post. PUT and DELETE are not shapes of their own; they are JavaScript helpers available inside a get_record or get_list snippet. The plugin needs the raw API key value, which every MCP response masks. The user copies it from the endpoint's dashboard page — a masked value fails authentication.

worker_list

ChatGPT
Use this when the user refers to one of their workers — by name, by what it does, or by asking what is available — and a worker name is needed to start a task. Not for registering or changing one: that is dashboard-only. Examples: "What workers do I have?", "Send this to our ERP", "Is there a worker that handles invoices?" Returns each worker's name and description, 10 per page with keyset pagination, optionally narrowed by a name search. A worker is an HTTP server the user runs, and it is not an endpoint — a task never touches one. 3Min API delivers tasks to it and the worker reports back. Each worker holds a URL, auth credentials, a signing secret and a callback key that are kept out of AI conversations; none of them appear here. Names are unique per user regardless of letter case. On Free, a worker is removed 7 days after it was registered. Building one: help(topic: "tasks") — read it when writing a worker, not to start a task.

api_call

Claude

collaborators

Claude

endpoints

Claude

help

Claude

logs

Claude

stats

Claude

subscription

Claude

task_cancel

Claude

task_create

Claude

task_get

Claude

task_list

Claude

wordpress_plugin

Claude

worker_list

Claude

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

App Stats

47

Tools

3

Prompts

ChatGPT, Claude

Platforms

Works with

ChatGPT
Claude

Data refreshed daily