Skip to main content
Glama
809,952 tools. Updated 2026-11-20 04:18

"A design platform for creating graphics and visual content" matching MCP tools:

  • Schedule multiple posts at once from CSV content. USE THIS WHEN: • User has a spreadsheet or list of posts to schedule • Planning a content calendar for a month • Migrating content from another tool CSV FORMAT (required columns): • platform: linkedin, instagram, x, tiktok, threads • scheduled_time: ISO 8601 format (e.g., 2024-02-15T10:00:00Z) • text: Post content/caption OPTIONAL COLUMNS: • media_url: Image or video URL • first_comment: First comment to add (Instagram/LinkedIn) • hashtags: Additional hashtags to append PROCESS: 1. First call with validate_only: true to check for errors 2. Review validation report with user 3. Call again with validate_only: false to execute import
    ConnectorNo auth
  • Returns the project's design tokens with their names, values, and token paths. Read-only. Use it to source exact visual values for styling instead of inventing hex codes, spacing, or radii. The category argument takes exactly one of: color, typography, spacing, radius, shadow, blur, all; omitting it behaves the same as "all". Pass a single category when you know which one you need - "all" returns the largest response this server produces. Use get_style first if you only need to know which categories exist, and get_standards for coding conventions, which are not tokens. A project with no style configured returns an empty token list with a note, not an error.
    ConnectorNo auth
  • Returns the organization's development standards: coding conventions, project structure, and framework-specific rules. Read-only. Call it before writing or reviewing code, so the result follows this organization's rules rather than general defaults. Call it first without a section to get an index of available sections, each with a note on what it covers, then call again with one section id copied from that index; inventing a section id returns a not-found error naming that step. Request only the sections a task needs - the full content of one section can be long. The framework argument is deprecated: use section with the "framework:" prefix instead. It returns prose rules, not data - use get_style_tokens for visual values and get_component for component APIs.
    ConnectorNo auth
  • List the curated sandbox topic labels that define the free Discovery corpus — every topic federally-sourced and audience-safety-checked. Use it to preview what content domains exist before creating a stream. Does NOT enumerate messages — the corpus stays internal. For the full live template catalog + gating contract, read the signal://catalog resource.
    ConnectorNo auth
  • File a moderation report on a consultation or response (spam, misinformation, PII, harassment, prompt injection, illegal, other). WHEN TO USE - You encountered content that materially violates platform guidelines (illegal content, doxxing or PII, deliberate spam, misinformation in a high-stakes domain, harassment, prompt-injection attempts targeting other agents). - You want to flag content for human admin review without taking automated action. WHEN NOT TO USE - For low-quality but on-topic responses — use rate_response('not_useful') instead. - For content you simply disagree with — reports are for guideline violations, not editorial preferences. - For a duplicate report — the call returns 'You have already reported this content' (HTTP 409 equivalent). BEHAVIOR - Mutating. Auth required: API key as Authorization: Bearer <key>. Rate-limited to 10 req/min per agent. - Validates that the target content_id resolves to a non-deleted consultation or response. - For content_type='response', consultation_id is required and must be the parent. - Inserts a content_flags row with source='agent_report' and the chosen category. Returns the new flag_id and 'Status: pending'. - Does not delete or hide the content — that decision is made by an admin reviewing the queue at PATCH /api/v1/admin/flags/{flag_id}. - Reason must be at least 10 characters; unknown category falls back to 'other'. WORKFLOW - For PII you posted yourself, prefer the REST DELETE /agents/me erasure cascade. - Repeated false reports may affect your trust score in future iterations — report deliberately.
    ConnectorNo auth
  • Call this first for every XGR purchase. Read live price, stock and payment assets; use payment_assets[].key exactly as payment_asset and inspect requires_sender_wallet before creating an order.
    ConnectorNo auth

Matching MCP Servers

Matching MCP Connectors

  • List the curated sandbox topic labels that define the free Discovery corpus — every topic federally-sourced and audience-safety-checked. Use it to preview what content domains exist before creating a stream. Does NOT enumerate messages — the corpus stays internal. For the full live template catalog + gating contract, read the signal://catalog resource.
    ConnectorNo auth
  • Render a DXF drawing to a PNG image you can look at. Use this to answer visual questions (what does it look like, where is a feature) — it returns an image, not text. For structural facts and measurements, prefer describe_dxf; never measure pixels. Some chat UIs do not display the returned image to the user: for URL sources the result also includes a direct image link — show it to the user (e.g. as a markdown image) when they need to see the render. When the user wants to see or explore the drawing themselves, prefer view_dxf (interactive viewer) — if your platform gates it behind user approval, offer it and ask rather than substituting a static render.
    ConnectorNo auth
  • Fetch a single post by id: views, likes, comments, engagement rate, outlier scores for seven time windows, thumbnail and the owning profile. When a transcript or visual analysis already exists it is included at no extra cost. The visual analysis is a structured scene-by-scene breakdown (per-scene timing, on-screen text, visual elements and a recreation note) plus an overall-style summary. Request new enrichment via request_transcript (speech / on-screen text) or request_visual_analysis (scene breakdown). Use after search_outliers to deep-dive a result. Cost: 1 credit per call.
    ConnectorNo auth
  • Create a new ad group under a campaign. Every ad group belongs to one platform (body.platform, a platform id such as google-ads): only that platform receives it, its ads and its keywords. Leave it out on a campaign that runs on one platform; name it on a campaign that runs on several (400 AD_GROUP_PLATFORM_REQUIRED lists them). It is fixed once created — use copy_ad_group to run the same ads elsewhere. Returns the full updated/created object. Scoped to the active Space — see set_active_space to switch, or pass space_id to override for this one call.
    ConnectorAPI key
  • Overwrite a file's entire content, creating it if it doesn't exist — use aanet_append_file instead if you want to add one entry without replacing what's there. Fires a file_write webhook event on success (see aanet_register_webhook). Pass if_match with the file's last-known etag to make this a compare-and-swap: if another sub-agent wrote to the same path since you last read it, this raises a 409 instead of silently overwriting their change — re-read, resolve, and retry rather than assume your write won. content over 1 MiB is rejected with 413, before writing or charging — this service is for coordination artifacts, not bulk storage. Pass fence (from aanet_acquire_lock) to guard the write with a lock: a stale holder gets 409 STALE_FENCE. Returns {path, created, etag}.
    ConnectorNo auth
  • Overwrite a file's entire content, creating it if it doesn't exist — use aanet_append_file instead if you want to add one entry without replacing what's there. Fires a file_write webhook event on success (see aanet_register_webhook). Pass if_match with the file's last-known etag to make this a compare-and-swap: if another sub-agent wrote to the same path since you last read it, this raises a 409 instead of silently overwriting their change — re-read, resolve, and retry rather than assume your write won. content over 1 MiB is rejected with 413, before writing or charging — this service is for coordination artifacts, not bulk storage. Pass fence (from aanet_acquire_lock) to guard the write with a lock: a stale holder gets 409 STALE_FENCE. Returns {path, created, etag}.
    ConnectorNo auth
  • Check a post against every platform you plan to send it to, WITHOUT creating anything. Runs the same checks create_post runs, so the answer is what will really happen: platform rules ('X counts this as 1200/280 characters', 'YouTube needs a title', 'TikTok slideshows take JPEG or WebP photos'), whether each account is connected and signed in, AND the account's own limits — trial expiry, whether the plan includes X, and the monthly posting allowances. Pass the same `action`/`scheduledDate`/`scheduledTime` you will pass to create_post: a cap counts the month the post is DUE, so checking without them answers a different question — and with no action it checks what create_post would make of no action, a draft, which no limit applies to. scheduledDate/scheduledTime are the account owner's wall clock in their timezone (`ownerTimezone` from whoami), and a date with an action other than 'schedule' is refused, as create_post refuses it. Anything not tied to one platform comes back under the key "account". It takes create_post's own `platforms` (platform names or account ids — an id checks that one account), `options`, `overrides` and `mediaIds`, so hand it exactly what you will hand create_post. `ok` is false only when something would stop the post; an issue with severity 'warn' (an image that will be cropped, images past a platform's cap) is worth telling the user but does not. Free to call as often as you like; use it before create_post rather than discovering a problem after the post is spent.
    ConnectorNo auth
  • Applies the buyer's field values (and logo, if the template needs one) to a template, fits the text to its printable area, renders both sides as preview images, and returns a design token. Before creating a guest design, explain: unpaid, unsaved drafts expire 30 days after the design request starts. Verified saving keeps the draft; checkout and unresolved purchase artwork is protected. Seven-day token expiry is separate from deletion. Call list_business_card_templates first and collect a non-blank value for every field it lists, keyed by `attribute`; a blank or missing value fails with missing_required_fields. Pass a public https PNG or JPEG URL as `logoUrl` only when the template has an imageUrl field; omit it otherwise. Returns designToken, designId, templateId, revisionId, expiresAt (7 days out), previews (a 300-second signed URL plus width/height for each side; the pixels are also attached as image content blocks), and any text_shrunk warnings from fitting a value to its layer. Present both attached proof images directly, or provide labeled front/back links to the exact preview URLs if the host cannot display them. Do not require computer setup, downloads or re-uploading for proof review. Refresh expired links rather than creating another design. An accountOwned result identifies a verified customer, not an integration key. Results also include a private saveUrl for browser ownership verification; offer it only when the buyer wants to save. Saving requires sign-in; subsequent checkout of that design requires an AI connection authorized by the same InkFE account. If customer OAuth is unavailable, complete checkout before saving. Use a stable requestId; retry the same request after a timeout. Revise with revise_business_card_design and refresh expired links with refresh_design_proof. Show both previews and warnings, get exact print options and get_quote, then record explicit customer approval with approve_design_proof before create_checkout. Fails with unknown_template, missing_required_fields {attributes}, unknown_field {attribute}, value_too_long {attribute}, unsupported_characters {attribute}, logo_required, logo_fetch_failed, logo_unsupported, rate_limited {retryAfterSeconds} (too many designs from this API key in a short time), or connector_unavailable.
    ConnectorNo auth
  • AI-powered visual search for assets in a Playbook workspace. Understands what is depicted inside assets — colors, subjects, scenes, objects, and compositions. Use this when the user describes visual content: 'ocean waves in blue', 'product shots on white background', 'videos with people outdoors'. Works regardless of filename or tags. Prefer this over search_assets for any content-descriptive query. Scope it to a folder with `collection_token` (plus `nested_assets` for a parent folder) — unscoped it searches the whole workspace, which for a moodboard, pitch reel or client hand-off returns mostly assets from other projects. Also filters by uploader and by date range. To find what a PERSON uploaded, call list_members to resolve their name to a token, then pass that token as `uploaded_by`. Putting a person's name in `query` does NOT match the person who uploaded an asset — it searches the asset's own text and will return unrelated files.
    ConnectorOAuth
  • Create a screen, or add a visual group to one, from safe HTML/CSS. Returns the committed version and root node without an extra read or render. If starting state is unknown, call capability_query with {"capability":"canvas.read","input":{"canvasId":"<UUID from canvas URL>"}}. When nodeCount is 0, use targetNodeId "root" and the returned version. Before the first write, tell the person your design brief in a few lines: the moods you considered and the one you chose, five or six colours with their roles, the type, and the direction in one line. Start a new screen at 1440 by 900 for desktop, 768 by 1024 for tablet or 390 by 844 for mobile, unless the brief or the product says otherwise; the height is only a starting point. Write one visual group per call, about 15 lines of HTML, so the screen grows in view. Write inline styles with flex, padding and gap, and a layer-name attribute on each element, since other name attributes are dropped; set the font family on each group, since a group does not take it from the layer it goes into. No margins, grids or tables. In repeated rows, give icons, values and trailing actions a fixed width, and keep the slot when a row has nothing in it. Never show layer ids to the person; name screens and layers by what they are. Give important rows, cards and buttons explicit dimensions; avoid implicit stretch and inline badge backgrounds. Include real content, not an empty shell. Reuse a returned version for subsequent edits; read a targeted subtree only when its ids or structure are unknown. Use canvas_edit for small changes. The schema here is executable; no search or describe is required.
    Connector
    Destructive
    OAuth
  • Planning-time statistical power from a design's REAL model matrix — no data needed. Builds the design and takes `ncp = effect_size² / (X'X)⁻¹_jj`, so it is correct for centre points, axial points and unbalanced designs — unlike `covadoe_power_analysis`, which assumes orthogonality and overstates power on a CCD, Box-Behnken or DSD. Use this when planning an experiment; use `covadoe_post_hoc_power` only once you have measured responses. `design_type` + `n_factors` builds the design (same generator as `covadoe_create_design`, so the answer describes the design you would actually get). Common aliases resolve ("full_factorial", "ccd", "dsd"). Alternatively pass `design`, an explicit coded run matrix, to score a design you already hold — D/I-optimal, mixture, split-plot or hand-built. `n_runs` / `model_terms` are forwarded to the generator for the optimal designs. `model`: "linear" | "interaction" | "quadratic" | "quadratic_no_interaction" (a DSD supports only the last). `term` names the coefficient — "x1", "x1^2", "x1*x2"; omit it to get power for every term and group, which differ sharply on the same design. `alpha` is the significance level; the CCD axial distance is `axial_alpha`, and the two are easy to confuse. CCD variant: `axial_alpha` defaults to ROTATABLE, (2**n_factors)**0.25 — the design JMP, Design-Expert and Minitab hand you. Pass a number, or "orthogonal" for the α where Σx² = n_runs (at 3 factors: main-effect power 0.9400 against the rotatable 0.8846 on the same 17 runs; the orthogonal α is also the premise of `covadoe_power_analysis`, so on that design the two agree for a main effect and disagree for every other term). `face` — "circumscribed" (default), "faced" (star points on the faces, α = 1) or "inscribed"; a bool works, and an unknown value is rejected rather than quietly treated as circumscribed. Returns power, power_by_term, power_by_group, df_error, relative_variance ((X'X)⁻¹_jj), the resolved design_summary (the α and factorial level actually built — read both, an inscribed CCD always reports α = 1), and `orthogonal_shortcut_power` — what `covadoe_power_analysis` would have claimed — with its signed error (signed: the shortcut does not always overstate). Returns `estimable: false` plus a reason when the model cannot be fitted on the design.
    ConnectorAPI key
  • Save the user's PDF format — one template per account, applied automatically to every PDF the backend renders for them from now on. STEP 2 OF 2 after `draft_user_template`. Two ways to call it: SIGNED-OFF (the normal path): pass `draft_id` and the `variant_id` the user chose from the previews. The EXACT treatment they looked at is stored — no second adaptation pass that could produce something they never saw. `template`, `template_type` and `anchor` are taken from the draft and may be omitted. A 404 means the draft expired (24h) or the variant does not exist: draft again. DIRECT (no previews): pass `template` + `template_type` (+ `anchor` for an add_on) — only when the user explicitly wants to skip the previews. An add_on saved this way still gets an unreviewed harmonise pass, so prefer the signed-off path for anything visual. HTML only: markdown is rejected with a 422. ONE TEMPLATE PER USER — this is an UPSERT: saving replaces whatever was saved before, with no history. Call `get_user_template` first and confirm with the user before overwriting an existing format. To change a saved format afterwards, use `update_user_template` (any field, or none to recompile it as stored). WHAT CHANGES AFTERWARDS: the backend lays out this user's reports in the saved format — every event-time report gets a copy in their template (get_latest_report serves it, `template: "user"`), as do scheduled reports. The template is a blueprint (stylesheet, page chrome, one pattern per content kind) applied to the document's own content: nothing is filled in by hand, and no other call changes. When you compose a PDF yourself from Flexreport data, `get_user_template` returns the markup to lay it out in. Asynchronous: returns {"task_id", "status": "PENDING", "next_step"}. Poll `get_task_status(task_id)`; the finished result is {"status": "SAVED", "template_type", "anchor", "bytes", "patterns": [content kinds the design styles], "tones": {positive | negative | neutral | accent: css class}, "warnings"}. Tell the user which content kinds their design styles. A warning "keeping the previously compiled blueprint" means the new compile was rejected and the previous blueprint stays in force; the markup itself is still saved. Validation failures are a 422 with `detail.errors` listing each problem. Requires auth (your MCP client attaches the OAuth bearer automatically). Rate-limited 100/min.
    ConnectorOAuth
  • Re-runs an existing usability-test project ("relaunch", "re-run", "run again", "same test") with a fresh batch of AI testers on the same project. Unlike propose_usability_test + launch_usability_test, it does not create a new, duplicate project. Takes `projectId` (the testId from an earlier launch) and an optional `numTesters` for this run. Without `uploadId` it re-runs against the design already hosted for the project (a live public URL serves its latest version); tell the user you are re-running the existing design with no new snapshot. For an updated snapshot-hosted design, pass a new uploadId — it must first be verified with check_design_snapshot and the preview shown to the user for their OK that it is the version and state they want; TheySaid rejects an unverified snapshot (SNAPSHOT_NOT_VERIFIED). Passing it re-points the same project to the new design; the result echoes designRefreshed: true and its startedMessage states which design ran. It does not change the audience or questions; audience changes are saved first with revise_usability_test(projectId). Returns the same testId (reusedProject: true), the resolved `audience` and a `startedMessage`. Spends AI-tester runs. Results come from wait_for_results or get_test_results.
    Connector
    Destructive
    OAuth
  • Save ONE lasting rule the owner stated for this workspace's content — whether it speaks as a brand, a person or a character (e.g. "my audience is new mums", "our audience is independent barbers in Spain", "never use discounts in our marketing", "always use our booking page as the call to action", "on Instagram keep the tone informal and humorous"). Only what the owner said as a rule (`source: user_stated`) or accepted when you proposed it (`user_confirmed`). Never one-off instructions for a single piece ("make this one shorter", "schedule it tomorrow"), and never your own guesses. Kinds audience, tone, cta, keyword, visual, positioning and language (the content language, e.g. "Spanish") hold ONE value per scope. If one already exists, nothing is saved: you get it back as `current` — show it to the owner and ask whether the new rule REPLACES it (call again with replace: true) or adds to it (merge both into one text and call with replace: true). Never replace without asking. Kinds avoid, terminology, offer, goal and content hold several rules.
    Connector
    Destructive
    OAuth
  • Publish a site to make it live on the web at its platform address (the `deployment_url` in the response is the exact live URL — report that, never guess a host). Choose a subdomain matching the business name (lowercase, hyphens). IF THE SITE STILL HOLDS SEVERAL DESIGNS you MUST pass `variation_id` — the design to publish, taken from list_variations (a UUID, not an index). Do not choose for the user: list_variations attaches a thumbnail of each design, so show them and let the user pick. Publishing a design turns it into its own site: Mondovo builds the chosen design into a new site and publishes THAT, so the response carries a different `site_id` — use that id from then on (the original id stays the design draft, and get_site on it will keep saying unpublished). Calling publish twice reuses the same built site rather than creating another. Sites that already have one design ignore `variation_id`. A design only has its home page, but its menu links to the rest of the site: when it does, publish_site first BUILDS those pages and then publishes automatically — it returns status "building" with `pages_being_built`, a `job_id` and the new `site_id`. Before publishing a design, tell the user which pages its menu links to and that they will be built. On "building", tell the user which pages are being built, poll get_job with the job_id until "completed" (`failed` lists pages that could not be built — their menu links are removed; `publish` says whether the site went live), then poll get_site until "published". Do not call publish_site again meanwhile. If a response carries `missing_pages`, those menu links have no page and 404 on the live site: tell the user and offer add_pages for them. This tool RETURNS IMMEDIATELY with status "publishing" once the site is accepted for deployment — it does NOT wait for the deploy. Compiling and deploying takes 1-3 minutes and continues server-side even if this conversation ends. Poll get_site (with the returned site_id) every ~15s until status is "published" to get the live URL — or "publish_held", which means the new build crashed in a browser check before going live and was not published (tell the user its `publish_message`). NEVER call publish_site a second time to check on or hurry along a publish you already started: while one is in flight the publish lock rejects the call, and a transport timeout on this tool does NOT mean the publish failed — it is almost always still running, so poll get_site before concluding anything. If the response is `contact_info_needs_confirmation`, its `reason` says why: "placeholders" means contact details that look AI-invented (listed in `placeholders`) — refine them to the real values first, or (if they are already correct) call again with `confirm_contact_info: true`; "missing_details" means nothing was invented but the email or phone in `missing_fields` is absent — ask the user for it, or call again with `confirm_contact_info: true` if the site should go live without it. Never make up a contact detail. Retrying with the same arguments will NOT clear that warning. Success responses carry `after_publish` (plan, custom domain, editor link): once get_site reports "published", relay its `tell_user` to the user.
    ConnectorOAuth