Zendesk MCP Server

Retrieve the content of a single section of an article in a given locale. Use get_article_outline first to discover section indexes. Default format="html" for round-trip safety. Pass format="markdown" only for human review — the Markdown representation is lossy on some structures (<pre> with <br>, tables with multi-<p> cells are kept as raw HTML to limit the damage, but do not round-trip markdown content back through update_article_section). The "## [n] hN: ..." line at the top is a label, not part of the content.

Get the currently authenticated Zendesk user. Useful to verify identity and permissions.

Description is built at runtime.

Retrieve a single organization by its numeric id. Returns full details (name, tags, domains, notes) — more than the name/id that search or list_organizations surface. Use list_organizations to browse or search for a name-based lookup.

Read one of the signed-in user's own requests, optionally with the whole conversation on it. Returns the request's status, the form it was submitted on, whether the user may mark it solved, and — with include_comments — every public message on it, each labelled with its author and marked when that author is a support agent. Internal agent notes are never returned on this path, so nothing agent-private can leak through it. A request belonging to someone else answers "permission denied" rather than "not found", so a denial here does not tell you whether that id exists. Find the number with list_…

Read what one request form actually asks for, so the user can be walked through it question by question. Returns the fields on that form in the order the portal shows them, each with its customer-facing label, whether it is required, and for dropdowns the exact values Zendesk accepts — plus any conditional rules ("if Type is Bug, Version becomes required"). Joins the form definition with the field definitions, because the form itself carries only field ids. Use it after list_request_forms and before create_request; omit form_id to describe the account default form. Conditional fields are repor…

Retrieve a Zendesk ticket by ID, including its live SLA state (per-metric stage and breach countdown) when an SLA policy applies, plus its comments if requested. Returns ticket details (subject, status, priority, assignee, tags, description) and optionally all comments/internal notes. It also lists the followers and email CCs on the ticket, resolved to names, which is how you tell who a ticket update actually reaches: followers are notified of updates including internal notes, email CCs take part in the public correspondence, and being the requester makes someone neither. Both lists come back …

Retrieve ticket attachments. Images are embedded inline; other files are listed as text references.

Read a ticket's change history — its audit trail — as a chronological, oldest-first timeline of who changed what and when. Each entry shows the actor (name and id) and the channel, then the field changes that update carried (status, priority, assignee, group, tags, custom fields) as before → after, with assignee/requester/group ids resolved to names. Comments appear as one-line presence markers (public comment vs internal note added), not their text — fetch the bodies with list_ticket_comments (or get_ticket(include_comments=true) for a short thread). Purely system-generated notification event…

Read the elapsed-time metrics (reply, resolution, wait and on-hold times, reopens, replies) of up to 100 tickets in one call. Each ticket gets first reply, first and full resolution, agent wait, requester wait and on-hold times in calendar and business minutes, plus reopen, reply, assignee-station and group-station counts and the key timestamps (assigned, solved, latest comment). These are facts Zendesk records on every ticket, so they are available even on tickets no SLA policy covers; they say how long things took, not how long is left — for the live breach countdown use get_ticket, search_t…

Retrieve a single user by their numeric id. Returns the full user record (name, email, role, organization, tags). Use search_users when you only have a name or email, or get_current_user for the authenticated identity.

Description is built at runtime.

List all attachments for an article. Returns attachment metadata only (id, file name, content type, size, URL), not the file bytes; both inline and block attachments are included. This is for Help Center articles — for attachments on support tickets use get_ticket_attachments instead. Upload new files with create_article_attachment.

List all available translations for an article (metadata only, no body: locale, title, draft, updated_at). Use get_article with locale for full translated content.

List articles (metadata only, no body). Use get_article for full content. Optionally filter by section ID and locale. Supports sort_by ("title", "created_at", "updated_at") and include_translations: true to show available translation locales per article. Note: include_translations must be re-sent on each paginated request.

List the Zendesk account's brands (id, name, URL, default/active flags) from the Support API. Multi-brand Guide accounts have one Help Center per brand: find the brand id here, then pass it as brand_id (id or subdomain) — REQUIRED on every brand-scoped Help Center tool in multi/all mode.

List all Help Center categories. Categories are the top level of the Guide hierarchy (category → section → article); each entry includes its id, name and locale. Results are cursor-paginated. Pair a returned category id with list_sections to drill down, then list_articles to reach articles. Pass a locale to read category names in that translation.

List the translations of a Help Center category: for each locale, the localized name, whether a description is set, and whether the translation is published or still a draft. Reach for this when a category looks wrong in a locale, because list_categories with that locale cannot settle it: a category with no translation is omitted from it, while a category whose translation is an unpublished draft may still be listed there under the draft name — so appearing in that listing does not mean published, and the draft flag here is what decides. Fix either case with set_category_translation; to sweep …

List Guide content tags, which are end-user-visible labels that help readers find related articles. Results are cursor-paginated (follow the returned cursor to enumerate the full list) and sorted by name by default. Pass name_prefix to look a tag up by the start of its name — do this before create_content_tag to reuse an existing tag rather than fragment the taxonomy. For internal, non-end-user search labels, see list_labels instead.

List all article labels. Labels improve Help Center search ranking and are not visible to end users. Attach them to an article through the label_names parameter of create_article or update_article.

List the active macros available to the authenticated user. A macro bundles a canned reply and/or a set of field changes (status, priority, assignee, group, tags, custom fields) an agent applies to a ticket in one gesture; this returns each macro id, title, description, availability scope, and its ordered list of actions, offset-paginated. Results are scoped by per-user OAuth to what the current user can see, so no shared admin key is needed. Pass a macro id from here to preview_macro_diff to preview its effect on a specific ticket.

List all organizations with pagination. Returns the name and id of each organization plus basic fields; results are cursor-paginated. Use get_organization with an id for full details (tags, domains, notes), or search for query-based lookups by name. Organizations group end users and can be referenced when creating or filtering tickets.

List all Guide permission groups. Use this to find the permission_group_id required when creating articles.

List the promoted ("featured") Help Center articles — the small, editorially-curated set surfaced at the top of their sections. Returns metadata only (no body); use get_article for full content. COST: the Help Center API has no server-side promoted filter, so this scans article pages (one Zendesk API request per page, up to ARTICLE_RESOURCES_SCAN_MAX_PAGES, default 20) and filters client-side — potentially costly on a large Help Center. Each call performs a fresh, uncached scan, so avoid calling it repeatedly. On a very large Help Center some promoted articles may be omitted, and both the omis…

List the kinds of request you can submit to this Zendesk — the forms a customer picks between on the Help Center, such as "Report a bug" or "Feature request". Returns each form's customer-facing name, its numeric id, and which one is the account default. Call this first when opening a request so the user chooses the right kind, then get_request_form to learn what that form asks for. Only forms that are active and visible to end users are listed; an account with a single form returns just that one. This is the end-user view: agents picking a form for someone else want list_ticket_fields and cre…

List the requests the signed-in user submitted, newest activity first by default. Returns each request with its number, subject, status and whether the user can mark it solved; pass a query to search their own requests by free text instead of listing all of them. Scoped to the caller by Zendesk itself — it can never return anyone else's tickets — which is why an agent calling this sees only requests they raised, not their queue. Use get_request to read one with its full conversation. Agents wanting a queue want list_tickets, search_tickets or get_view_tickets instead.

List the translations of a Help Center section: for each locale, the localized name, whether a description is set, and whether the translation is published or still a draft. Reach for this when a section looks wrong in a locale, because list_sections with that locale cannot settle it: a section with no translation is omitted from it, while a section whose translation is an unpublished draft may still be listed there under the draft name — so appearing in that listing does not mean published, and the draft flag here is what decides. Fix either case with set_section_translation; to sweep every c…

List Help Center sections. Sections are the middle level of the Guide hierarchy (category → section → article) and group related articles; each entry includes its id, name, category_id and locale. Results are cursor-paginated. Pass category_id to list only one category's sections (ids come from list_categories), then use a section id with list_articles. Pass a locale to read section names in that translation.

List the SLA metrics that are breached or about to breach across a set of tickets, most urgent first. Pick the set with exactly one of scope (mine, my_groups or all unsolved tickets), view (a Zendesk view by title or id) or query (any Zendesk ticket search). Each running metric that is breached, or closer to its breach than its CRITICAL or WARNING threshold, is one line under BREACHED, CRITICAL or WARNING, soonest breach first, with the ticket id, metric, time left or overdue, subject, status and priority; paused and achieved metrics never appear. Thresholds are per metric family (reply metric…

List the configured SLA policies with their filter conditions and per-priority reply/resolution targets. Use this to explain why a given target applies to a ticket and to reconstruct deadlines deterministically instead of hard-coding the policy matrix. Requires an admin token (or a custom role granted the SLA-management permission); a standard agent token gets 403 here, though it can still read live per-ticket SLA via get_ticket / search_tickets.

Read a ticket's conversation — public replies and internal notes with their full bodies — one cursor-paginated page at a time, newest comment first. Each entry carries the comment id, the author resolved to a name, the timestamp, whether it is public or internal, and the ids of any attached files. Prefer this over get_ticket(include_comments=true) whenever a thread is long or you only need the latest exchange: get_ticket appends the thread as one unpaginated block and cuts it past the response character limit, which drops the most recent comments first. Keep sort_order "desc" (the default) to …

List the ticket field definitions configured on this Zendesk (both system fields and custom fields), returning each field's id, type, whether it is active/required, and — for dropdown and multiselect fields — the valid option values. Use this to discover the numeric field ids and accepted option tags that create_ticket and update_ticket expect in their custom_fields argument, so a natural-language intent ("set severity to High") maps to the right id and a value Zendesk will accept instead of a blind guess. Read-only reference lookup; cursor-paginated in Zendesk's default field order.

Description is built at runtime.

List all user segments. User segments control article visibility (who can view). Use the ID when creating or updating articles.

List the agent's active Zendesk views — the saved ticket queues ("Unassigned tickets", "My open tickets", "Breaching today") the agent sees in the Zendesk UI — each with its current ticket count so you can tell at a glance where the workload sits. Views are per-agent scoped, so per-user auth returns exactly the queues this agent can see, with no shared key. Counts come from Zendesk's cache and can lag by up to about an hour (shown as "(count updating)" while a fresh value is still being computed); pass a view's title or id to get_view_tickets to read the tickets inside it.

Add or remove tags on a ticket. Performs an incremental read-modify-write: it fetches the ticket's current tags, adds those in `add` and deletes those in `remove`, then saves the merged set — tags you don't list are left untouched and duplicates are collapsed. Adding a tag already present, or removing one that is absent, is a no-op (idempotent). Returns the ticket's full tag set after the update. Use this for incremental tag edits; to overwrite the entire tag set at once, or to change tags alongside other fields, use update_ticket instead. Find the ticket id via search_tickets or list_tickets.

Close one of the signed-in user's own requests, for when they consider it resolved. Returns the request's status read back from Zendesk, not merely an acknowledgement: this operation is refused unless the request is actually solvable by its requester, because Zendesk answers 200 and changes nothing when it is not, which would otherwise be reported as success. A request is only solvable once an agent has been assigned to it, so a brand-new or unassigned one cannot be closed this way — leave it, or reply with add_request_comment to say it is no longer needed. Marking an already-solved request so…

Preview the exact changes a macro would make to a specific ticket, as a before → after diff, WITHOUT saving anything. Orchestrates two reads — the ticket's current state and Zendesk's macro-apply preview (which returns the whole resulting ticket) — and returns only the fields the macro actually changes (status, priority, assignee, group, tags, custom fields) plus the canned reply with its public/internal flag; unchanged and identity fields are omitted. Nothing is committed: to apply it, follow up with update_ticket for the field changes and add_public_comment or add_private_note for the reply.…

Description is built at runtime.

Dev only. Re-imports the Zendesk tool modules from source and re-registers them on this live session, so tool code you just edited takes effect without restarting the server or reconnecting the client. Call it once at the end of an edit cycle, before testing your changes; the refreshed tool list is announced via tools/list_changed (a client on the 2026-07-28 revision receives it only on an open subscriptions/listen stream; otherwise call tools/list again). Only the tool modules (tickets, search, help_center, users) are reloaded — edits to shared infrastructure (HTTP client, shared definitions,…

Reorder an article within its current section by moving it relative to its siblings (top, bottom, or before/after another article), and return whether the new order was applied. This is the reliable way to satisfy "put this article first/last" requests: it writes the minimal set of article positions needed to make the order deterministic, because Zendesk leaves newly created articles tied at position 0 where a plain position update is silently ambiguous. It does NOT move the article to a different section — use update_article with section_id for that. Zendesk exposes no way to read whether a s…

Search across tickets, users, and organizations. Supports filters like "type:ticket status:open", "type:user role:agent". Returns total count and paginated results (25 per page by default, up to 100); a ticket description is cut to a 200-character excerpt, which get_ticket returns in full. Organization results include name and ID only — use get_organization for full details (tags, domains, details).

Full-text search across Help Center articles (metadata only, no body). Use get_article for full content. Supports locale filtering. Returns total count.

Description is built at runtime.

Search for users by name, email, or other criteria using Zendesk search query syntax. Returns total count.

Create or update the translation of a Help Center category in one locale, and return the resulting translation (locale, localized name, draft state). Creates the translation when the locale has none and updates it otherwise, so no listing call is needed first; only the fields you pass are written, which makes "publish this draft" a single draft: false. Use it to make a category reachable in a locale where its sections or articles are already translated — a gap find_translation_gaps reports and list_categories cannot explain.

Create or update the translation of a Help Center section in one locale, and return the resulting translation (locale, localized name, draft state). Creates the translation when the locale has none and updates it otherwise, so no listing call is needed first; only the fields you pass are written, which makes "publish this draft" a single draft: false. Use it to make a section reachable in a locale where its articles are already translated — a gap find_translation_gaps reports and list_sections cannot explain.

Update article metadata only (draft, promoted, labels as label_names, content tags as content_tag_ids, visibility as permission_group_id / user_segment_id, section_id, sort position, etc.) and return the updated article. Does NOT update content (title, body) — use update_article_translation for that.

Replace the body of one article section, heading excluded (the heading is kept as is), in a given locale, leaving the rest of the article intact. The server fetches the current body, replaces the targeted section, and PUTs the full reconstructed body via the Translations API. A leading heading in content that repeats the section heading is removed; any other h1-h3 in content creates new sections and shifts the later indexes (the response warns). section_index 0 is the heading-less intro, which exists only when the body has text before its first heading. Default format="html" for fidelity. Use …

Update article content (title, body) in a specific locale. For targeted edits on one or a few sections, prefer update_article_section — this tool replaces the FULL body and re-sends the entire article on each write. Use the article's source_locale (from get_article) for the default language, or another locale for translations.

Update an existing ticket (status, priority, type, assignee, group, subject, tags, custom fields, followers, email CCs). Only the fields you pass are changed, and the updated ticket is returned. Followers and email CCs are incremental instead of replacing: pass { add, remove } lists of user ids, and the response reports who is subscribed afterwards. Zendesk applies those two silently, so a requested change it did not apply comes back listed as unconfirmed rather than raised as an error. Setting tags here replaces the whole tag set — use manage_tags to add or remove individual tags without over…

Description is built at runtime.