The MCP tool directory.

Unlocks access to other MCP tools. All tools remain locked with a "Session Not Initialized" error until this function is successfully called. Skipping this explicit initialization step will cause all subsequent tool calls to fail. MANDATORY FOR AI AGENTS: The returned instructions contain ESSENTIAL rules that MUST govern ALL blockchain data interactions. Failure to integrate these rules will result in incorrect data retrieval, tool failures and invalid responses. Always apply these guidelines when planning queries, processing responses or recommending blockchain actions. COMPREHENSIVE DATA SOURCES: Provides an extensive catalog of specialized blockchain endpoints to unlock sophisticated, multi-dimensional blockchain investigations across all supported networks.

Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc

Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc

Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc

Get platform info, pricing, usage stats, or documentation.

Whether Google Search Console is connected, when the 14-day trial ends, and whether Pro access is active. Does not query Search Console and does not include a price.

Whether Google Search Console is connected, when the 14-day trial ends, and whether Pro access is active. Does not query Search Console and does not include a price.

Whether Google Search Console is connected, when the 14-day trial ends, and whether Pro access is active. Does not query Search Console and does not include a price.

List your connected Minter.io reports (social media accounts). Returns all reports the user tracks. Optional: filter by platform ("instagram", "tiktok", "x", "facebook", "linkedin", "threads").

List all accounts in your Cloudflare account

Get details about specific GitHub Actions resources. Use this tool to get details about individual workflows, workflow runs, jobs, and artifacts by their unique IDs.

Tools for listing GitHub Actions resources. Use this tool to list workflows in a repository, or list workflow runs, jobs, and artifacts for a specific workflow or workflow run.

Trigger GitHub Actions workflow operations, including running, re-running, cancelling workflow runs, and deleting workflow run logs.

Activates a flow's version for an environment, making it live for API calls. Activates the latest version by default, or a specific version by ID. The entrypoint template must have a model configured (set one via update_flow_template) — activation fails otherwise. Activation locks the version (it becomes read-only; editing it again forks a new draft). Returns the environment -> version mapping after activation.

Makes a tool version the definition that runs in one environment see (e.g. dev, demo, prod). A run pins its tool versions when it starts, so runs already in progress are not affected.

[write] Write Facebook/Instagram ad copy for an ad image URL: headline, primary text, description, CTA, and hook angle. Returns up to 5 variations. Pass projectId so the copy uses the brand brief. Call this right after a generation completes.

List the ad-copy messaging styles (clickbait, professional, UGC, direct response, storytelling, ...) accepted by adCopyGeneration.generate.

Addition calculator that adds two numbers

Adds two numbers together

Add review comment to the requester's latest pending pull request review. A pending review needs to already exist to call this (check with the user if not sure).

Appends one or more pre-decided content ideas to a workstream. Use this when you have specific articles in mind rather than letting the AI propose them. Each idea defaults to contentType=BlogPost, contentRole=Support, targetWordCount=1000 (Support) or 3000 (Pillar), status=Idea. Pass a brief at creation to skip generate_brief_for_idea later; once status is set to ApprovedForGeneration, call generate_content_from_idea to produce the article.

Adds a DNS record to a custom domain, e.g. MX and TXT records to set up an email provider, or TXT/CNAME verification records. Types: A, AAAA, CNAME, MX, TXT, SRV. For MX give the mail server hostname as value plus priority. For SRV give "priority weight port target" as value.

Add a comment to a specific issue in a GitHub repository. Use this tool to add comments to pull requests as well (in this case pass pull request number as issue_number), but only if user is not asking specifically to add review comments.

Start tracking a keyword. kind is "brand" (default), "competitor" or "topic". platforms optionally restricts it to some platforms (default: every platform). New mentions containing the term will be matched, classified and delivered. For a common word, narrow it with `matching` (requiredTerms with requiredMode any|all, excludedTerms with a `*` wildcard at an end, excludedAuthors, caseSensitive): a post the rules reject is never stored or billed. `context` is one sentence the classifier reads for this keyword only ("Arc is our browser; ignore the geometry word"). `cap` ({ mentions: N }) is a monthly ceiling on its matched mentions: at the cap it stops matching until the first of the next month (UTC) or until the cap is raised, while its daily keyword charge continues. `groupId` puts it in a keyword group (list_groups; default: the workspace's default group); a term may be tracked once per group, so two groups may track the same term as two keywords. `reviewSources` collects reviews: pass each page's link (url: an App Store or Google Play app, a Trustpilot page, a Google Maps place or its maps.app.goo.gl share link) or platform (appstore|googleplay|trustpilot|googlemaps) and id; the app stores also take countries (two-letter codes, default us) and Google Play a language (default en). Every review of the page becomes a mention of this keyword, polled daily, and the last 30 days (newest 100) come in free at once. `platforms: []` makes a reviews-only keyword.

Adds the brand's own material to a research dossier — their measurements, their usage numbers, what their customers told them, what they observed. It is turned into claims marked primary, which the writer prefers over every source on the web and which are exempt from the two-publisher rule that governs web claims. This is the material nobody else writing about the topic has. Pass suggestionId to answer one of the dossier's suggested primary research items; it is then marked answered.

Add a reply to an existing pull request comment. This creates a new comment that is linked as a reply to the specified comment.

[write] Queue a FINISHED AD image render. Required: projectId. Call adResearch.listProjects first and pick the project the request is about, or ask the user when it is ambiguous; never guess an id. Also required: prompt, a creative brief rather than a finished image prompt. How the prompt is used: a creative-director model rewrites it into the real image prompt using the project's brand brief, and that rewrite always adds a specific headline, a subline, a CTA button, and the project logo when the project has one. Negative instructions in the prompt ('no text', 'no logo', 'nothing but the product') cannot suppress those; use adGeneration.generateImage when the caller wants exact or no text. Optional: adType, aspectRatio, quality (low/high/ultra), referenceImageUrls, inputImageId (from upload.uploadImageBase64), referenceAdId or referenceInspirationId to remix an existing ad. Costs credits. Returns a generation ID. Poll adGeneration.getById until status is COMPLETED.

[write] Queue an image-to-image edit and return immediately. The universal edit tool: change background, restyle, swap a subject, change aspect ratio, add brand assets, or remix a competitor ad. Source is either sourceAdId (one of the user's own generations) or sourceImageUrl (any direct image URL). Costs credits. Poll adGeneration.getById until COMPLETED.

[write] Queue an image render from a VERBATIM prompt. The prompt goes to the image model exactly as written: no creative-director rewrite, no brand brief, no added headline, subline or CTA, and no project logo. The image contains only what the prompt stipulates. Use this when the caller wants only specific stipulated text, forbids text/logos/CTAs, or wants raw scene, product, or photography imagery rather than a finished ad; use adGeneration.create for finished ads. Required: projectId (credit scoping only, nothing from it enters the prompt) and prompt. Optional: aspectRatio, quality (low/high/ultra), referenceImageUrls and inputImageId for image-to-image. Costs the same credits as adGeneration.create. Returns a generation ID. Poll adGeneration.getById until status is COMPLETED.

Get the status, prompt, and resulting image URLs of a single ad generation by ID. Use to poll until status is COMPLETED.