Adobe Customer Journey Analytics
Run cross-channel reports and build segments in Adobe Customer Journey Analytics.
Run Wolfram|Alpha queries, search the docs and evaluate Wolfram Language.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
Wolfram's hosted MCP server gives Claude, ChatGPT and any MCP client a computational back end. Three tools do the work: one queries Wolfram|Alpha in plain English, one searches Wolfram documentation, and one evaluates Wolfram Language code in a cloud kernel. No sign-in. That third tool is a general-purpose programming language, and it is the whole story of this page.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Uses semantic search to retrieve any relevant information from Wolfram. Always use this tool at the start of new conversations or if the topic changes to ensure you have up-to-date relevant information. This uses semantic search, so the context argument should be written in natural language (not a search query) and contain as much detail as possible (up to 250 words).
Evaluates Wolfram Language code for the user in a Wolfram Language kernel. If a formatted result is provided as a markdown link, use that in your response instead of typing out the output. Parse natural language input with `\[FreeformPrompt]["query"]`, which is analogous to ctrl+= input in notebooks. Natural language input is parsed before evaluation, so it works like macro expansion. You should ALWAYS use this natural language input to obtain things like `Quantity`, `DateObject`, `Entity`, etc. This is a stateless kernel, so you cannot reuse definitions from previous evaluations.
Use natural language queries with Wolfram|Alpha to get up-to-date computational results about entities in chemistry, physics, geography, history, art, astronomy, and more.
Read from the server on 2026-08-18, including each tool's own safety annotations.
readOnlyHint: true, destructiveHint: false. Only Wolfram's prose separates the evaluator from the two search tools, and it does so clearly. Grade the risk by the code argument, not the flag.agenttools.wolfram.com uses, and the AgentTools repository documents the *absence* of sandboxing for customer-deployed cloud servers. We tested nothing and claim nothing beyond that.code string on every call, which gets awkward fast.timeConstraint is 60 seconds. Long computations must be raised per call or broken into steps.WolframContext is degraded without a subscription. Wolfram's repository states that without LLMKit it provides no reranking or filtering and returns no Wolfram|Alpha results — so on the free endpoint it is a documentation search, not a knowledge search.429 behaviour for this endpoint. The Wolfram|Alpha developer API's published 2,000 non-commercial calls per month is a *different* product's limit and should not be read onto this one.initialize capability block declares neither. Both list methods return empty arrays rather than an error, but the capability block is authoritative.2025-03-26. We requested 2025-11-25 and 2025-06-18; both returned 2025-03-26. Clients depending on newer protocol features will not get them here.initialize, tools/list, prompts/list, resources/list, resources/templates/list and three deliberately empty tools/call requests made to observe the auth gate. Every behavioural claim above comes from Wolfram's documentation or the tool schemas.No, not at this endpoint. We opened an anonymous handshake on 2026-08-18 and the server returned all three tool definitions without a credential. We then called each tool with empty arguments and got a parameter validation error rather than an authentication challenge, which means the request cleared any gate. Wolfram describes the hosted service as free for limited personal use.
Wolfram's own setup guide says no. It recommends always allowing the Wolfram|Alpha and Wolfram Context tools while setting the Wolfram Language Evaluator to require approval. All three tools carry identical readOnlyHint true annotations, so the annotation does not make that distinction and the vendor's written guidance does. Treat code evaluation as code evaluation.
One answers questions, the other finds syntax. Wolfram's agent-facing documentation describes WolframAlpha as natural language queries for direct factual lookups, and WolframContext as semantic search of Wolfram documentation used to locate the right function before calling the evaluator. WolframContext returns reference material about Wolfram Language, not computed answers about the world.
No. The tool description states this is a stateless kernel and that definitions from previous evaluations cannot be reused. Wolfram's own product comparison labels the hosted Cloud MCP as one-shot stateless and says it does not support sessions. We confirmed the transport behaves that way, answering tools/list with no session identifier and with an invalid one alike.
No. The connector is a remote HTTP service, so code runs in Wolfram's cloud rather than on your computer. Wolfram's comparison table states the hosted Cloud MCP does not support external files and supports neither upload nor download, and lists local file access as a Local MCP feature instead. Nothing in the three schemas accepts a file path.
Because repeat calls are not guaranteed to match. Many Wolfram computations are deterministic, but the same tools also answer questions about current time, live financial and astronomical data, and random sampling. A query about today returns a different result tomorrow. The annotation is set for the tool as a whole, so the weakest case governs all three.
No, and no key is needed, but the licence matters more than the price. Wolfram calls the hosted service free for limited personal use and publishes no numeric call quota. Its general Terms of Use separately state the Services should not be used alongside your own AI-powered tools or services unless a separate licensing agreement is in place, which affects commercial embedding.
documentation value is https://www.wolfram.com/artificial-intelligence/mcp-service/, which 301-redirects to the /artificial-intelligence/mcp/cloud/ URL cited here. Source for "Remote/Cloud/One-shot stateless", "Does not support sessions", "Does not support external files", "Free for limited personal use", "For small-scale and casual use", the Cloud-versus-Local comparison and the Q&A section. Read as Markdown via the index.en.md affordance advertised in Wolfram's llms.txt. · retrieved 2026-08-18https://agenttools.wolfram.com/mcp is the hosted endpoint. · retrieved 2026-08-18README.md, docs/tools.md, docs/servers.md and docs/cloud-deployment.md from raw.githubusercontent.com. Wolfram's own MIT-licensed toolkit, whose default server configuration is exactly these three tools. Source for the WolframContext LLMKit degradation, the 60-second TimeConstraint default, the stateless-evaluation-model description and the cloud deployment security note about no built-in sandboxing in v1. That security note is written about servers a customer deploys to Wolfram Cloud; we do not extend it to Wolfram's own hosted endpoint. · retrieved 2026-08-18initialize, tools/list, prompts/list, resources/list, resources/templates/list and three empty tools/call requests against https://agenttools.wolfram.com/mcp (2026-08-18). All returned HTTP 200 anonymously. tools/list returned 3 tools with descriptions, JSON Schemas and annotations; each empty tools/call returned a missing-parameter message rather than an authentication challenge; resources/templates/list returned -32601. Source for the tool count, every annotation state, the capability block, the protocol downgrade, the stateless session behaviour and the auth posture. · retrieved 2026-08-18x-data-source-information response header the MCP server itself returned). Source for the curated-primary-sources description and the dataset enumeration. · retrieved 2026-08-18x-terms-of-use response header the MCP server itself returned, which advertises http://www.wolfram.com/legal/terms/wolfram-cloud.html; that URL 301-redirects to the general terms cited here, and no Wolfram Cloud-specific terms document exists at the destination. Source for the AI-powered-tools licensing clause, the AI-training prohibition and the scraping/bulk-download prohibition. The document contains no sandboxing, rate-limit or resource-limit statement. · retrieved 2026-08-18Sandbox symbol and no sandboxing tutorial (both 404 on 2026-08-18). · retrieved 2026-08-18Connect Wolfram once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.