Dataslayer MCP server
Yes. Dataslayer publishes an official MCP server at https://mcp.dataslayer.ai/mcp. It's hosted. It offers 16 tools. We last checked it on 22 Nov 2026.
Official: answers MCP requests at mcp.dataslayer.ai, on Dataslayer's own domain dataslayer.ai. Checked 22 Nov 2026. Maintained by Stuart Brameld.
Key facts
As of 22 Nov 2026, Dataslayer's official MCP server scores 61/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 56 of our 56 checks in the last 90 days and lists 16 tools.
How the Agent Readiness Index works · Wrong? Suggest a correction
Dataslayer MCP server review
61/100
Dataslayer's MCP server scores 61/100 on MartechDB's Agent Readiness Index: easy to connect an AI agent to, with a few gaps.
The good
Hosted by Dataslayer: connect by URL, with nothing to install
Answered 100% of our checks in the last 90 days
Free trial
No card needed to start
The bad
Agent access costs more than the base plan
Not checked yet: how you sign in; a docs page listing its tools. Anything not checked scores nothing.
Official MCP server
Dataslayer MCP server
- Address
- https://mcp.dataslayer.ai/mcp
- Runs
- Hosted
- Sign-in
- Cost to use
- Plan: Advanced and above · Free trial · No card needed · Costs more than the base plan100 messages a day on Advanced and Pro; custom limits on Business
- Official MCP Registry
- Not listed
- How we know it's official
-
- Answers MCP requests at mcp.dataslayer.ai, on Dataslayer's own domain dataslayer.ai.
- Tools
- 16 tools · listed 22 Nov 2026
- First seen
- 1 Oct 2026
- Last checked
-
Reachable ·
16 Nov 2026: reachable17 Nov 2026: reachable18 Nov 2026: reachable19 Nov 2026: reachable20 Nov 2026: reachable21 Nov 2026: reachable22 Nov 2026: reachable
- Uptime
- 100% · 56 of 56 checks reachable since 1 Oct 2026
Dataslayer MCP server tools (16)
As the server lists them. Names and descriptions are the vendor's own.
-
get_available_datasourcesGet available datasourcesUse this when the user asks which datasources are available through a shared link, which datasources their Dataslayer plan lets them use, or which ones they could add by upgrading. For a shared link, returns only the datasources shared by that link and allowed by the owner's plan or trials; no upgrade catalog. Use it to list or count that link's datasources. For their shared connections and accounts, use get_available_connections_and_accounts_info_by_datasource. Without a shared link, returns the plan catalog: what they are ALLOWED to use, not what they have connected. For "how many / which data sources do I have?", "my connected sources" or "¿cuántas fuentes de datos tengo?" without a shared link, use get_hub_connections instead. Returns three lists of {"id", "name"}: - available_datasources: the datasources of the user's plan, beta ones included; - other_datasources: datasources they could use by upgrading the plan; - trial_datasources: usable only while a trial of a Dataslayer serv…
-
get_hub_connectionsGet connected datasourcesUse this when the user asks which or how many data sources they have connected, e.g. "how many / which data sources do I have?", "my connected sources" or "¿cuántas fuentes de datos tengo?" without a shared link. For a shared link, use get_available_datasources instead; this account-wide tool is unavailable. Count only the datasources whose list of connections is not empty. For what the plan allows (trials included) use get_available_datasources; for the accounts inside the connections use get_available_connections_and_accounts_info_by_datasource. Returns every datasource id with its connections; an empty list means not connected: { "<datasource_id>": [{"id": "<connection id>", "is_shared": <bool>, "shared_by": "<email>"}], "<datasource_id>": [], ... } On an error, read error_code and follow next_step. OUT_OF_SCOPE through a shared link directs you to get_available_datasources; call it to answer which datasources the link shares.
-
get_manage_ads_connectionsGet advertising management connectionsUse this when finding write-authorized connections for advertising and content management. Do not use it to change objects or query reporting data. Returns each datasource's supported and connected flags and its authorized connection ids; these are logins, not ad account ids. The list follows the current plan. A supported datasource without a management connection includes a single-use log_link, valid for 10 minutes: give it to the user to authorize writing. Reporting connections alone do not grant writing. After login, return to this conversation and call this tool again to verify; the link itself does not confirm success. An exact return_url enables browser return; without one the completion page asks the user to close the window and return to chat. On an error, read error_code and follow next_step. A shared link sees only its shared datasources and management connections; it cannot create a new management login.
-
get_manage_ads_fieldsGet advertising management fieldsUse this when collecting advertising or content management inputs. Call before manage_ads. Do not use for reporting fields or to perform a change. Returns a JSON Schema for core data inputs, required fields and alternatives, the complete accepted field-name list, and provider-specific guidance. Optional fields outside the core schema and account/objective-specific requirements are validated by the provider. This metadata does not confirm management authorization. A shared link can use this tool for a datasource it shares. On error, read error_code and follow next_step. For create, edit and delete, call get_manage_ads_fields for all requested objects before asking for inputs. Review nested schemas, alternatives and provider notes. Ask for all missing required and conditional values together in the first clarification message, not one field or step at a time. Include dependent objects and format/objective-specific choices; label conditions when a choice is unknown. Reuse supplied values…
-
verify_facebook_object_existsVerify Facebook objects or list account pagesUse this only when the user needs to verify that one Facebook campaign, ad set, ad creative, or ad id exists and is accessible to a management connection, or to list available Facebook page ids and names for an ad account while creating ads. Object verification performs a read-only GET by exact id; page listing uses the supplied ad account id. Do not use this tool for analytics or reporting; use natural_to_data for reporting data. On error, read error_code and follow next_step. A shared link can use only its shared Facebook management connections.
-
manage_adsManage advertising adsUse this when listing or changing ads/content. Not for reporting. Get connection_id from get_manage_ads_connections, keeping its full suffix. Get inputs from get_manage_ads_fields. For edit/delete, get exact ids from prior results or natural_to_data; clarify ambiguous matches. Success confirms completion; in-progress does not. Poll check_task_id; never resubmit while waiting. Edits apply the same data to every id. On error, follow next_step. Shared links use only shared connections. deletion_pending=true confirms the deletion request, not completed removal. For create, edit and delete, call get_manage_ads_fields for all requested objects before asking for inputs. Review nested schemas, alternatives and provider notes. Ask for all missing required and conditional values together in the first clarification message, not one field or step at a time. Include dependent objects and format/objective-specific choices; label conditions when a choice is unknown. Reuse supplied values; do not ask…
-
get_available_fields_by_datasourceGet datasource fieldsUse this when the user asks which metrics, dimensions or options a datasource has, e.g. "which CTR metrics does Facebook Ads have?". Do not use it to get data: use natural_to_data. Returns "metrics" and "dimensions" as {"id", "aliases", "type", "category", "concept", "common"} (compact false adds each field's "description") and "options" with their possible values. Use the returned ids as they are; never invent one. The answer can be large: narrow it with field_type, category, search_text, common_only or limit. A search_text that finds nothing answers a "message" saying what to try next.
-
get_available_connections_and_accounts_info_by_datasourceGet datasource connections and accountsUse this when the user asks which accounts, properties or sites they have in one datasource, or for the schema of a "database" connection. Do not use it to get data (use natural_to_data) or to list the connected datasources (use get_hub_connections). Returns "connections" ({"id"}), "accounts" ({"id", "name", "connection_id"}), for "database" the "database_schema" of each connection id and, when the datasource has no connection, a "log_link" where the user connects one in the Dataslayer Hub, also said in "message": give the user that link. Connection ids include permission and sharing suffixes such as (read/write, shared by ...). Copy each id unchanged; the bare email may identify a different connection without write access. For Bing, each account also includes customer_id (its owning Customer ID); use its id as ad_account_id and its customer_id together for advertising management.
-
natural_to_dataQuery marketing dataUse this when the user asks for marketing or analytics data: metrics by dimensions for some accounts and dates, e.g. "clicks by campaign in Facebook Ads last month". Pass the whole request in `question`; the tool resolves the datasource, accounts, fields and dates and runs the query. Do not use it for questions outside marketing or analytics, or only to list datasources, fields or accounts (use the other tools for that). One datasource and one period per call: to compare datasources (Google Ads against Facebook Ads) or periods (September against September last year), call it once for each. When the user refines a previous query, restate it with the change, so the accounts, metrics, dimensions and connections they did not change stay the same. ALWAYS: For shared-link users, provide descriptive analysis only: report results, trends and comparisons supported by the data. Do not recommend actions, optimizations or strategies to improve performance. If asked for advice, explain that shared…
-
dataslayer_subscription_informationGet subscription informationUse this when the user asks about their Dataslayer plan, limits, usage, renewal or company, e.g. "which is my plan?", "when is my plan renewed?", "what are my Google Sheets limits?" or "how many users are in my company?". Returns "account_details": email, first_name, last_name and "company" (name, owner: the user the subscriptions belong to, users_in_company; empty when the user has no company). And "subscriptions_details", per service the user has started (a missing service was never used): - quota_limit (-1 means unlimited), limit_type ("query": one per call, "row": per returned row), limit_frequency ("daily": resets at 00:00 UTC, "monthly": resets on sub_start_day) and current_usage; the usage left is quota_limit - current_usage. - plan: name, is_trial, start_date, expiration_date, billing_cycle (MONTHLY or YEARLY), subscription_type (custom or Stripe) and is_cancelled (true: it does not renew, but works until expiration_date). - account_limit, has_blend_active, has_ai_insights_act…
-
manage_alertsManage AI alertsUse this when the user wants to create, update, delete, list or run an AI alert, or see the execution history of one. Pass the whole request in `question`; the tool works out the operation and its parameters. Structured clients may provide `request` with an empty question to save exact settings, including active state and alert_metadata, without another model or provider lookup. Both modes use the same account, API and stored alert IDs. - create: needs what to watch (datasource, metric, accounts) and the condition, e.g. "alert me when the Facebook Ads spend of account X goes over 100". What the user leaves out is filled in (a name from the request, weekly frequency at the frequency's default day and hour, the user's timezone): the answer gives the name, frequency, scheduled_time and timezone used; tell the user. - update: only the fields the user names change. - update, delete, run and get_history need the alert id or name; ask for it when the user did not give one or it matches sever…
-
manage_data_transfer_schedulesManage data transfer schedulesUse this when the user wants to create, update, delete, list or run a data transfer schedule, or see the execution history of one, for these destinations: BigQuery, AWS Redshift, AWS S3, Snowflake, Google Cloud Storage, Database, Azure SQL and Azure Storage. To list Google Sheets or Excel schedules use get_schedules_from_user. Pass the whole request in `question`, naming the destination. Destination parameters, all needed to create one: - BigQuery: project_id, dataset_id, table_id, destination_email - AWS Redshift, Snowflake, Database, Azure SQL: table_name, connection_id - AWS S3, Google Cloud Storage, Azure Storage: upload_path, file_name, connection_id - create: needs the data to transfer (datasource, metrics or dimensions, accounts and dates, as for natural_to_data), the destination parameters and the frequency (hourly, daily, weekly, monthly or selected hours); ask the user for what they did not give. Optional: the time, timezone (the user's by default), name and write mode (upse…
-
check_task_idCheck query statusUse this when checking whether a query or advertising change has finished. After manage_ads returns "in-progress", call this with its task_id to complete the authorized operation; do not ask for permission again or resubmit the mutation. For natural_to_data, check only when the user asks. Do not use this to start a new task. Copy task_id exactly. Status "success": the finished result. "in-progress": still running; tell the user to ask again later. "warning": it finished without data. "error": its error_code says why (the query failed, or UNKNOWN_TASK: a task_id not copied exactly or expired); follow its next_step.
-
get_schedules_from_userGet Google Sheets and Excel schedulesUse this when the user asks which Google Sheets or Excel schedules they have saved. Read only: it cannot create or change schedules. For data transfers to warehouses or storage use manage_data_transfer_schedules. Pass destination when the user said Google Sheets or Excel. Returns the schedules (document, type, timezone, query parameters, last execution, created and modified dates); status "success" with an empty list means the user has none. Show every field returned.
-
get_special_datasource_call_type_hints_toolGet special datasource hintsUse this when the user asks how to request data from a special datasource (google_trends, google_pagespeed, google_keyword_planner, applovin, instagram_public_data, facebook_public_data, youtube_public_data), or to know which call_type to pass to get_available_fields_by_datasource for one of them. Returns, per special datasource, its "call_types", the "extra_args" each one takes and "notes". To get data, write those values (usernames, page ids, keywords...) in the question of natural_to_data: it takes no other argument.
-
get_next_paginated_resultGet next page of resultsUse this only when the user asks for the next page of a query result, giving the task_id that natural_to_data returned. Do not call it on your own, and do not use it to start a new query. Pass the task_id exactly as given; page_token is not needed: each call gives the page after the last one given. Returns the next page and, when more pages remain, a next_page_token. "error" with NOT_FOUND: there are no more pages, tell the user; any other "error": follow its next_step.
Connect your AI to Dataslayer
Add the official Dataslayer MCP server to Claude, ChatGPT or your editor.
Connect Dataslayer MCP to Claude
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it Dataslayer, paste the address below and click Add.
Connect Dataslayer MCP to ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it Dataslayer and paste the address below.
ChatGPT usually only connects to servers with self-serve sign-in or none.
Connect Dataslayer MCP to Cursor
Opens Cursor if it's installed. If nothing happens, use the JSON below.
Connect Dataslayer MCP to VS Code
Opens VS Code if it's installed. Otherwise add the JSON settings from the Cursor tab to your .vscode/mcp.json.
Dataslayer MCP server questions
Does Dataslayer have an official MCP server?
Yes. Dataslayer publishes its MCP server itself. Its address is on Dataslayer's own domain (mcp.dataslayer.ai). MartechDB only lists servers a vendor publishes, never community copies.
What is the Dataslayer MCP server URL?
The address is https://mcp.dataslayer.ai/mcp.
How do I connect Dataslayer MCP to Claude, ChatGPT or Cursor?
In Claude, add https://mcp.dataslayer.ai/mcp as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http dataslayer https://mcp.dataslayer.ai/mcp
What can the Dataslayer MCP server do?
It offers 16 tools, including get_available_datasources, get_hub_connections, get_manage_ads_connections, get_manage_ads_fields and verify_facebook_object_exists (as listed on 22 Nov 2026). 13 are marked read-only and 3 can delete or overwrite data.
Is the Dataslayer MCP server in the official MCP Registry?
No. Dataslayer hasn't published it to the official MCP Registry.
Is the Dataslayer MCP server free to use?
No, it needs a paid plan, after a free trial. No card is needed to start. Plan needed: Advanced and above. It costs more than the base plan. Limits: 100 messages a day on Advanced and Pro; custom limits on Business. From Dataslayer's own pages, checked on 7 Oct 2026.
Is the Dataslayer MCP server working?
Yes. It answered our most recent check. We last checked it on 22 Nov 2026.
What are the alternatives to Dataslayer's MCP server?
In Marketing reporting & dashboards, the most agent-friendly alternatives with an official MCP server are Chartbrick (100/100), DashThis (98/100), Databox (97/100), Supermetrics (97/100) and Oviond (97/100). Dataslayer scores 61/100 on the same index.
Alternatives to Dataslayer's MCP server
Vendors in Marketing reporting & dashboards with an official MCP server, the most agent-friendly first. Dataslayer scores 61/100.
Chartbrick
chartbrick.com
DashThis
dashthis.com
Databox
databox.com
Supermetrics
supermetrics.com
Oviond
oviond.com
Change history
What we've seen change for Dataslayer, newest first.
-
Dataslayer: Dataslayer MCP server: 4 tools added (now 16)
Use with AI
Connect your AI to MartechDB
Then ask it about Dataslayer, or any of the 1,850 marketing tools with an official MCP server. Free, no sign-in.
Claude.ai and Claude Desktop
Open Customize, then Connectors.
Click +, then Add custom connector.
Name it MartechDB, paste the address below and click Add. There's no sign-in.
The free plan allows one custom connector. On Team and Enterprise plans, an owner adds the connector first.
Claude Code
Run this in your terminal:
ChatGPT
Open Settings, then Apps, then Advanced settings.
Turn on Developer mode, then click Create.
Name it MartechDB, paste the address below and choose No authentication.
Developer mode is on Plus and Pro plans, and on Business, Enterprise and Edu if an admin allows it.
API
The same data as JSON, with no sign-in. See the OpenAPI description for every endpoint and field.
CLI
Search the directory and print the command to connect a vendor's server, from your terminal. Needs Node 18 or later. View on npm
Show that your MCP server is verified
If you work at Dataslayer, add this badge to your MCP docs or README. It's free, it's the same for every vendor, and it updates from our daily checks: it shows uptime while the server responds, and says so if it stops.
Something wrong or out of date? Suggest a correction or email us, and we'll check it against the evidence. Every correction we make is listed on Corrections.