MCP server

Connect your AI assistant to your Trust Center

Move your trust page over from another platform, keep it current, and read what your visitors are doing, from Claude or any MCP client. One tenant per connection, your own role as the ceiling, and nothing publishes without a person.

https://mcp.delivertrust.io/mcp

Move your trust page over from another platform

Already on SafeBase, Drata, Conveyor, UpGuard or Vanta? Point your assistant at the public page and it builds the DeliverTrust version: branding, certifications, sub-processors, controls, FAQ and custom pages. You review the plan before anything is written. The assistant cannot publish; when you are happy with the result, you publish from the admin app as you do today.

  1. Connect your AI assistant and choose the tenant you are moving into.
  2. Give it the public URL of your current trust page and ask it to migrate.
  3. Review the plan it returns: every write, in order, plus the gaps it found.
  4. Let it apply the plan. Then, when you are happy with the result, publish from the admin app as you do today; the assistant cannot publish.

Try: “Migrate our trust page from https://trust.example.com into DeliverTrust”

  • SafeBase
  • Drata
  • Conveyor
  • UpGuard
  • Vanta

Document files stay behind each platform’s NDA and never migrate; the document inventory does. Only public content is read. Both are stated again in the limits below.

Get started

No API keys. You sign in with your DeliverTrust account and choose what the connection may do.

Claude (web and desktop)

  1. Open Settings, then Connectors.
  2. Choose Add custom connector.
  3. Name it DeliverTrust and paste the server URL.
  4. Sign in with your DeliverTrust account when the browser opens, pick the tenant, review the permissions and choose Authorize.
https://mcp.delivertrust.io/mcp

Claude Code

  1. Add the server from the terminal, then run /mcp inside a session to sign in.
claude mcp add --transport http delivertrust https://mcp.delivertrust.io/mcp

Other MCP clients

  1. Any client that supports remote MCP servers over HTTP with OAuth can connect. Register the server URL in its configuration; the sign-in and consent steps are the same.
{
  "mcpServers": {
    "delivertrust": {
      "url": "https://mcp.delivertrust.io/mcp"
    }
  }
}

The tools 70

21 read tools and 49 write tools, grouped by what they act on. Each card names the permission it needs, in the words the consent screen uses; your assistant only sees the tools its connection was granted. This list is generated from the server, so it is never behind it.

Your connection

  • Connection contextread
    get_auth_context

    Report which DeliverTrust tenant this connection is authorized for, who authorized it, and what it is permitted to do.

    Permission: Your connection

  • Authorizable tenantsread
    list_tenants

    List the DeliverTrust tenants this person could authorize a connection for, and which one this connection is bound to.

    Permission: Your connection

Migrate from another platform

  • Plan a migrationread
    migrate_trust_page

    Plan a migration of a public trust page on SafeBase/Drata, Conveyor, UpGuard or Vanta into this tenant: reads the source, mirrors its certifications, sub-processors, controls, FAQ, overview and custom pages as the ARGUMENTS of the write tools (set_branding, edit_certifications, edit_subprocessors, edit_controls, the page and logo tools, set_layout), and reports every gap - gated content, documents (inventory only), in-progress claims, dead links.

    Permission: Read your trust pages

Your trust page

  • Read trust pageread
    get_trust_page

    Read the tenant's trust page as its editors see it.

    Permission: Read your trust pages

  • Platform catalogsread
    get_catalogs

    DeliverTrust's curated catalogs of controls, certifications and sub-processors, for picking well-known entries to add to this tenant's page with the edit_* library tools.

    Permission: Read your trust pages

  • Version historyread
    list_versions

    List the stored earlier versions of one stream of trust page content: a library (controls, sub-processors, certifications), the rail branding, the hero, the overview, the request-workflow content, or one page (section=pages with page_id, deleted pages included).

    Permission: Read your trust pages

  • Restore a library versionwrite
    revert_library

    The person wants a library put back the way it was - "undo that", "restore the sub-processors from before this morning", "put the certifications back".

    Permission: Edit trust page content

  • Restore a section versionwrite
    revert_section

    The person wants one of these put back the way it was - "undo the overview change", "put the old hero title back", "restore the NDA text from yesterday".

    Permission: Edit branding (logo, colors, contact email)

Branding

  • Set brandingwrite
    set_branding

    Set the tenant's wordmark name, hero and navigation colours, and navigation placement.

    Permission: Edit branding (logo, colors, contact email)

  • Set logo from URLwrite
    set_branding_logo

    Set the tenant's hero/wordmark logo from an image URL (PNG, JPEG, SVG or WEBP, 1 MB max).

    Permission: Edit branding (logo, colors, contact email)

  • Set favicon from URLwrite
    set_favicon

    Set the public page's browser-tab favicon from an image URL (PNG, JPEG, SVG or a real .ico, 1 MB max; an .ico is converted to PNG).

    Permission: Edit branding (logo, colors, contact email)

Controls

  • Edit controlswrite
    edit_controls

    The person asks to add, change or remove one or more controls, or a category - "add 'MFA on every admin account' under Access control with this description", "rename Identity to Identity and access", "remove the legacy VPN control".

    Permission: Edit trust page content

Sub-processors

  • Edit sub-processorswrite
    edit_subprocessors

    The person asks to add, change or remove one or more vendors - "add Datadog under Infrastructure", "our CDN moved to Cloudflare", "remove Segment".

    Permission: Edit trust page content

  • Attach vendor logowrite
    set_subprocessor_logo

    Attach a vendor's own logo (PNG, JPEG, SVG or WEBP URL, 1 MB max) to one entry of the sub-processor register by vendor_id.

    Permission: Edit trust page content

Certifications

  • Edit certificationswrite
    edit_certifications

    The person asks to add, change or remove one or more certifications or compliance marks - "add ISO 27001", "rename SOC 2 to SOC 2 Type II", "remove the HIPAA mark".

    Permission: Edit trust page content

  • Attach badgewrite
    set_certification_logo

    Attach a badge image (PNG, JPEG, SVG or WEBP URL, 1 MB max) to one certification by certification_id, so the mark renders the badge rather than a monogram.

    Permission: Edit trust page content

Pages and FAQ

  • Restore a page versionwrite
    revert_page

    The person wants a page put back the way it was - "undo that edit to the privacy page", "bring back the FAQ from this morning".

    Permission: Edit trust page content

  • Restore a deleted pagewrite
    restore_deleted_page

    The person deleted a page and wants it back - "undo that delete", "restore the terms page I removed".

    Permission: Edit trust page content

  • Create pagewrite
    create_page

    Create a custom page on the trust page: a rich-text page (Terms, Privacy, a security overview) or an FAQ page (question groups).

    Permission: Edit trust page content

  • Update pagewrite
    update_page

    The person asks to change a custom page's text, path or title, or an FAQ page's groups and questions - "update the privacy page", "add a question to the FAQ", "remove the question about data residency".

    Permission: Edit trust page content

  • Delete pagewrite
    delete_page

    The person asks to remove a custom page or an FAQ page - "delete the old terms page".

    Permission: Remove pages

  • Add page imagewrite
    add_page_image

    Add an image to a custom page's body from an image URL: it is fetched, moderated and stored, and the result's html is the <img> snippet to place in the page body.

    Permission: Edit trust page content

Documents

  • Upload documentwrite
    upload_document

    Upload a document (SOC 2 report, pentest summary, policy) from a URL (pdf, docx, xlsx, pptx, png, jpg, md, txt; 25 MB max) and list it under a category on the page's Documents section.

    Permission: Manage documents (upload, edit, remove)

  • Update documentwrite
    update_document

    Change a document's name, description or access gates (nda_mechanism, approval_mechanism, identity_mechanism) by document_id.

    Permission: Manage documents (upload, edit, remove)

  • Delete documentwrite
    delete_document

    The person asks to remove a document from the trust page - "take down the old SOC 2 report".

    Permission: Manage documents (upload, edit, remove)

Layout

  • Replace layoutwrite
    set_layout

    The person asks to move, resize, hide or show a section, change the hero or overview text, or the page needs resizing after a library write.

    Permission: Edit trust page content

  • Add Overview imagewrite
    add_layout_image

    Add an image to an Overview or FAQ rich-text field from an image URL: it is fetched, moderated and stored, and the result's html is the <img> snippet to place in that field.

    Permission: Edit trust page content

Updates

  • Read updatesread
    list_updates

    Read the trust page's Updates: every update, drafts included, newest first, each with its entries and ids, plus whether Updates is enabled and its access level.

    Permission: Read your trust pages

  • Create updatewrite
    create_update

    Post a new security notice, incident follow-up or compliance news item on the trust page's Updates tab.

    Permission: Post and remove trust page updates

  • Change updatewrite
    update_update

    Add a follow-up entry to an update, correct an entry, publish or unpublish it, or put it on the Overview card.

    Permission: Post and remove trust page updates

  • Delete updatewrite
    delete_update

    The person asks to remove an update entirely.

    Permission: Post and remove trust page updates

  • Email update subscriberswrite
    email_update_subscribers

    "Email subscribers now" for an entry that was posted without email.

    Permission: Post and remove trust page updates

  • Read update subscribersread
    list_update_subscribers

    Read who subscribes to the trust page's Updates: every row with its email, status (pending until they confirm, active, unsubscribed), source (visitor or admin) and dates, plus counts per status.

    Permission: Post and remove trust page updates

  • Add update subscriberwrite
    add_update_subscriber

    Add someone to the trust page's Update emails, as the admin Add subscriber dialog does.

    Permission: Post and remove trust page updates

  • Remove update subscriberwrite
    remove_update_subscriber

    The person asks to take someone off the Update emails - "remove j.okafor@fabrikam.example from our updates".

    Permission: Post and remove trust page updates

  • Updates settingswrite
    set_updates_settings

    Turn the trust page's Updates on or off, or set the one access level every update shares: Public (none/none), Email sign-in (none/none with identity_mechanism=email; no NDA), click-through NDA (click_through/none) or NDA plus manual approval (click_through/manual).

    Permission: Post and remove trust page updates

Request workflow

  • Set request workflowwrite
    set_request_workflow

    The person asks to change the blocked email domains, the generic-mailbox block, the NDA text, one of the three visitor emails or the visitor-facing copy.

    Permission: Edit request workflow

Access requests

  • Access requestsread
    get_access_requests

    The tenant's document access requests: the queue awaiting a human decision (who asked, for which documents, when) and the recent history.

    Permission: Read access requests

  • Decide access requestwrite
    approve_access_request

    The person asks to approve or reject a pending document access request - "approve Jane's request", "reject the request from the gmail address".

    Permission: Manage access requests (approve, reject)

Analytics

  • Trust page analyticsread
    get_analytics

    How the trust page is doing over a trailing window (7d, 30d, 60d or 90d): page views, unique visitors, top referrers, visitor actions, and the access-request funnel.

    Permission: Read visitor analytics

Data export

  • Export all datawrite
    export_tenant_data

    Prepare and download a full export of this tenant's data as one zip: every trust page store as JSON with every saved version, uploaded documents and images in their original form, questionnaires and approved answers, access requests, NDA acceptances, the access ledger and the audit log.

    Permission: Download a full export of all your data, including gated documents and visitor records

Feedback and roadmap

  • Send feedbackwrite
    send_feedback

    Send feedback to the DeliverTrust team: a bug, a missing feature, or a problem hit mid-migration.

    Permission: Roadmap sentiment and feedback

  • Read roadmapread
    get_roadmap

    Read the DeliverTrust product roadmap: each planned item with its vote counts and the connected user's own vote.

    Permission: Read the DeliverTrust roadmap

  • Vote on roadmapwrite
    set_roadmap_vote

    Set or clear the connected user's vote on a roadmap item: wont_use, neutral, would_use or need_it, or clear=true to remove it.

    Permission: Roadmap sentiment and feedback

Questionnaires

  • Get an upload URLwrite
    create_questionnaire_upload

    Get a 15-minute signed URL to upload a local file: a customer's questionnaire (.xlsx, .csv, .docx; 5 MB) or, with purpose=evidence, an evidence file.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Preview a questionnaireread
    preview_questionnaire_import

    Read an uploaded questionnaire the way the admin app's import does: three readers find each sheet's question column, answer column and question rows, and flag rows they disagree on.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Import a questionnairewrite
    create_questionnaire

    Import an uploaded questionnaire with the sheets and rows the person confirmed (preview_questionnaire_import's suggested_sheets, adjusted).

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • List questionnairesread
    list_questionnaires

    List the tenant's imported questionnaires, newest first: id, name, file name, question count and import date.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Questionnaire usageread
    get_questionnaire_stats

    Questionnaire usage, all time and the last 30 days: answers generated, answers accepted, questionnaires completed, and each questionnaire's approved and total counts.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Read a questionnaireread
    get_questionnaire

    Read a questionnaire's answers: each item's n, sheet, row and question, its status and status_label, answer_text (empty when there is no answer to give), answer (the sources' one-word verdict: yes, no, partially, describe or not_stated, for a Yes/No column; it does not follow the person's own final_answer), the quoted evidence lines with their sources, and whether it is approved.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Answer a questionnairewrite
    answer_questionnaire

    Draft answers for a questionnaire's waiting questions from the tenant's own sources, for up to about 35 seconds per call.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Answer a questionnaire againwrite
    rerun_questionnaire

    The person added evidence or answers after a questionnaire was answered and wants fresh answers - "answer the Acme review again".

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Edit answerswrite
    update_questionnaire

    Rename a questionnaire, set the person's own answer on a question (final_answer), or approve or unapprove it, by n from get_questionnaire.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Export a questionnaireread
    export_questionnaire

    Write the answers into the customer's own workbook (each answer into its row's empty answer cell; evidence only with include_evidence, in a new column; a .csv or .docx becomes a new workbook) and return a 15-minute download URL.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Delete a questionnairewrite
    delete_questionnaire

    The person asks to remove a questionnaire - "delete the Acme review".

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Ask a questionread
    ask_questionnaire_question

    Answer one security, privacy or compliance question from the tenant's own sources, the way the admin app's Ask box does.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Read answer settingsread
    get_questionnaire_settings

    Read what questionnaire answers may draw on: which documents and pages (all, chosen or none), the Overview, Controls, Subprocessors and Updates switches, and external URLs.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Change answer settingswrite
    set_questionnaire_settings

    Change what questionnaire answers draw on.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • List answer sourcesread
    list_answer_sources

    List every source answers can use right now, each with its access level, status (ok, or why it could not be read) and line count; never its text.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • List evidence filesread
    list_evidence_files

    List the questionnaire evidence files: files answers may draw on that never appear on the trust page (an internal pen-test summary, an insurance schedule), with id, name, description and size.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Upload evidence filewrite
    upload_evidence_file

    Add an evidence file from an upload: get a URL with create_questionnaire_upload(purpose=evidence), PUT the file, then call this with its upload_id.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Rename evidence filewrite
    update_evidence_file

    Change an evidence file's display name or description by evidence_id.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Replace evidence filewrite
    replace_evidence_file

    Swap an evidence file's contents for a newer upload, keeping its id, name and description.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Delete evidence filewrite
    delete_evidence_file

    The person asks to remove an evidence file - "drop the old pen-test summary".

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • List approved answersread
    list_approved_answers

    List the approved answers: one list of the answers people wrote themselves (origin manual, such as the legal name or EIN) and the approved questionnaire answers marked for reuse (one entry per question however it was asked).

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Add an answerwrite
    add_approved_answer

    Add an answer of your own (a question and its answer, such as the legal name or EIN) to the approved answers.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Edit an answerwrite
    set_approved_answer

    Edit an approved answer by entry_id.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Remove an answerwrite
    remove_approved_answer

    The person asks to drop an old or wrong answer - "remove the 2024 insurance answer".

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Set answer categorywrite
    set_approved_answer_category

    Set an approved answer's category (privacy, data security, platform security, corporate security, company information, product capabilities, legal and contract, support and SLAs) by entry_id.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

  • Resolve a possible duplicatewrite
    resolve_possible_duplicate

    list_approved_answers shows an entry with a suggestion and the person decides whether it asks the same thing as its twin, or wants a pair in kept_apart flagged again.

    Permission: Answer questionnaires from your documents, including NDA-gated ones (beta)

How authorization works

OAuth 2.1 with PKCE, the standard the major AI clients speak. Tokens last an hour under a connection that lasts 30 days of use and can be revoked at any time.

  1. Sign in

    Your AI client opens a browser window to app.delivertrust.io. You sign in exactly as you do for the admin app, MFA included. The client never sees your password.

  2. Pick one tenant

    A connection is bound to a single Trust Center, chosen on the consent screen. Every tool call is checked against that choice, so an assistant cannot wander into another tenant you belong to. To work on a second tenant, connect again and pick it.

  3. Choose the permissions

    Read access is always granted. Writing is opt-in by area: content, branding, documents, page removal, the request workflow, access requests. The permissions you grant are a ceiling under your own role: an Editor cannot grant an assistant more than an Editor can do.

  4. Work, and keep the last word

    The tools are described so that an assistant reads before it writes and confirms the change with you first. Every write lands in your Audit Logs with the same actor and detail as a hand edit, and the connection itself is logged when it is made, refreshed and revoked.

What it does not do

Stated plainly, because a limit you find out about mid-migration is worse than one you read here first.

  • It cannot publish your trust page

    Publishing and unpublishing are not grantable over MCP, and neither are changing your URL or custom domain, managing members, or deleting a tenant. An assistant can prepare a page; a person publishes it in the app.

  • Document files never migrate

    Every platform keeps its files behind an NDA or an access request. When you bring a trust page over, the document inventory comes with it and the files do not. You upload those yourself.

  • Only public content migrates

    The migrate tool reads what a visitor can read. A FAQ that a platform lists but does not answer publicly, or a sub-processor detail behind a login, is reported as a gap rather than invented.

  • A vendor security score is not carried over

    UpGuard shows a security score that has no equivalent in DeliverTrust. The migrate tool reports it as a deliberate omission and never writes a number in its place.

  • A Vanta FAQ page beyond the overview is reported as a gap

    Vanta pages are read through a real browser. The overview, certifications, sub-processors and controls are read; a FAQ page holding more than the overview is reported with counts, not partially imported.

  • Served badge images expire after 30 minutes

    Compliance badges rasterized from a Vanta page are served at short-lived URLs. Apply a migration plan while it is fresh. Past the expiry the image fetch is refused, and running the migration again produces a fresh plan with fresh images.

  • Confirmation before a write is best-effort

    The tool descriptions ask the assistant to confirm each change with you before writing. DeliverTrust cannot force a client to do so, which is why the permissions you grant, and your own role, are the hard limits.

  • You revoke your own connections

    Connections belong to the person who made them. An Administrator cannot revoke another member's connection; that member does it from Connected apps, or their access ends when their membership does.

Disconnecting

Every connection you have made is listed under Settings › Connected apps in the admin app, with the client, the tenant and when it was last used. Revoke ends every token under it immediately. By authorizing a connection you confirm you are authorized to act for that company and accept the Terms of Service.

Log in to the admin app

Questions

Is my trust page content sent to the AI provider?

When you ask your assistant something, it calls a DeliverTrust tool and the result goes back to the assistant to answer you. What the AI provider does with that is governed by your agreement with them, not with DeliverTrust. Grant read-only access if that is all you need.

Can one connection cover several tenants?

No. A connection is bound to one tenant at consent, on purpose. An assistant that could choose the tenant per call is one that can name the wrong one confidently. Connect once per tenant you want to work on.

What does a migration actually do?

It reads the public trust page you point it at (SafeBase or Drata, Conveyor, UpGuard, Vanta), maps it onto a DeliverTrust trust page, and returns a plan: the exact writes, in order, plus a summary and a list of gaps. Nothing is written until you have reviewed the plan and the assistant applies it with the write tools you granted. The assistant cannot publish your trust page; when you are happy with the result, you publish it from the admin app, exactly as you do today.

How do I disconnect?

Open Settings › Connected apps in the admin app and revoke the connection. Every token under it stops working immediately. Removing the connector inside your AI client is not guaranteed to revoke it on our side; Connected apps is the place that is.