WORKSPACE.PM turns Claude into a project assistant that knows your real data: status, risks, workload, portfolio. Connected in two minutes through a connector, with each person's own permissions, operated in Germany. Works today, on every Claude plan.
Claude with the WORKSPACE.PM connector
Campus North is amber. 2 of 5 milestones done, 3 open risks, of which 1 critical (facade delivery delay). Cost positions: 1.2 million planned, 0.9 million committed.
Open in WORKSPACE.PMClaude writes good status reports when you give it the numbers. With the WORKSPACE.PM connector it fetches them itself: current, complete and only what the person asking is allowed to see.
Executives and steering committees ask Claude for the state of a project or the whole portfolio and get the answer in seconds, with a link to the source. The status round becomes a decision round.
Leaders no longer wait for the report. They ask.
A risk surfaces while talking to Claude? It creates it, measure included. A capacity question before a commitment? It checks the assignments. Time entry, Kanban card, lessons learned: done without switching applications.
Fewer context switches, better maintained data, because maintenance happens on the side.
The connector is available on every Claude plan, including the free one. A project lead can start this afternoon; IT decides through the role gate what external AI clients may do. Scales from a single seat to Claude Enterprise with centrally managed connectors.
No procurement project before the first benefit is visible.
Real working situations, real answers from WORKSPACE.PM. Every answer links back to the object in the system.
Prompt
How is project Campus North doing: milestones, open risks, cost positions?
Result
Claude pulls the figures from WORKSPACE.PM and answers with clickable links to the project, its risks and the latest report.
Module: Project statusPrompt
Create a risk in project Campus North: facade delivery delay, likely, high impact, measure: request second supplier.
Result
If the person's role has write access for AI clients, Claude creates risk and measure after your confirmation. The audit trail records channel MCP and the client.
Module: Risk managementPrompt
How much free capacity does the Construction Management team have in November, and which projects compete for it?
Result
Claude answers from the assignments the person is allowed to see anyway. Whoever has no resource view does not get one through Claude either.
Module: Resource managementPrompt
Summarise for Friday all critical risks, the decisions from the timeline and the scenarios in portfolio Digitalisation.
Result
The brief is built from live data, not from last week's slide. Every point carries the link to the original, and Claude writes it out for you.
Module: Portfolio scenariosPrompt
Which of my cards in the current sprint have open checklist items?
Result
Claude lists the person's own cards with open items and links each one directly. Only projects the person is a member of are visible.
Module: Kanban and sprintsPrompt
Record as a lesson learned for Campus North: bind the facade supplier earlier, anchor a second source in the contract.
Result
Claude creates the entry in the project after your confirmation. The conversation becomes knowledge the next project will find.
Module: Lessons learnedNo IT project, no agent building. The person enters the connector address and signs in with their WORKSPACE.PM account. On Claude Team and Enterprise an owner creates the connector once, centrally; after that every person connects individually.
In Claude go to Customize, Connectors, click the plus sign and then Add custom connector. Give it a name and enter the MCP address of WORKSPACE.PM; your administrator finds it in the Integration Hub.
Claude opens the WORKSPACE.PM sign-in. The consent screen shows application, account, tenant and scope. If SSO via Microsoft Entra ID or another identity provider is enforced, it applies here as well.
From now on Claude answers questions from your project data. Before tool calls Claude asks; you decide per tool whether to allow once or always. Write access exists only if your role allows it for AI clients.
According to Anthropic documentation as of September 2026. WORKSPACE.PM needs no AI provider of its own and no second contract for this route.
| Plan | Custom connector | Who sets it up | Training on your chats |
|---|---|---|---|
| Claude Free | yes, one connector | the person | on by default, can be turned off in privacy settings |
| Claude Pro and Max | yes, several | the person | on by default, can be turned off in privacy settings |
| Claude Team | yes, centrally | organisation owner, then each person | no, commercial terms |
| Claude Enterprise | yes, centrally | organisation owner, then each person | no, commercial terms |
Recommendation for organisations: Claude Team or Enterprise, because the connector is managed centrally there and chats are not used for training. For a first test any plan will do.
For IT, CISO and data protection
The connector is deliberately not a service account. Each person signs Claude in as themselves, WORKSPACE.PM checks every call server-side, and your IT limits per role what external AI clients may do. What Anthropic does with the chat history is governed by your Anthropic plan.
Identity
Each person signs Claude in as themselves, via OAuth 2.0 with PKCE. No service account, no shared token. The consent screen names the application, the account, the tenant and the scope.
Sign in to WORKSPACE.PM
The application acts with exactly your permissions.
Permissions
Claude acts with exactly the permissions of the signed-in person, checked server-side with roles and row-level security. On top of that you limit per role what external AI clients may do: nothing, read only or write.
External AI clients per role
The gate can only narrow permissions, never widen them.
Traceability
Every change triggered through Claude is written to the audit trail with channel MCP, the acting person and the name under which the client registered, linked to the changed object and filterable by source.
Connected people
Risk R-18 created
M. LangCard K-204 moved
S. KernData flow and contracts
Claude connects from Anthropic's cloud to the MCP endpoint and retrieves data. WORKSPACE.PM sends nothing to Anthropic on its own and runs no AI model of its own for this route. There is no broker in between and no additional store.
Your contract with Anthropic
Claude
connector in your account
DPA with WORKSPACE.PM
WORKSPACE.PM
MCP endpoint, Germany
The Claude connection works the same in all three operating models. What changes is who runs the endpoint.
Operated in German data centres, DPA under Art. 28 GDPR, no US sub-processor for project data.
Your own instance, operated by us, in Germany or in the data centre you specify.
Your own operation. The MCP endpoint of your installation must be reachable from the internet over HTTPS, for example through a reverse proxy.
Purely internal installations without internet ingress cannot connect Claude. For public sector clients: on-premises and managed hosting in Germany, connection optional and switchable per role.
Security and data protectionThe four questions that come up in every security review, answered with what the product actually does.
No. Every answer is computed under the identity of the person asking. Confidential projects remain invisible, including for search and evaluation. What Anthropic stores from the answer is governed by your Anthropic plan.
Write tools can be blocked completely per role or limited to reading. Claude asks before every tool call unless you allow permanently; in the system the person's normal rights apply in addition. Every change is marked as an MCP change in the audit trail.
WORKSPACE.PM stores no questions you ask Claude and no answers. Stored per person are the number of requests, the time of last use and the client, plus every change with channel MCP. The chat history lives with Anthropic, under the rules of your plan.
MCP is an open standard. The same endpoint works with Microsoft Copilot, ChatGPT or local models. If you change the assistant, the connection stays. And you can switch the integration off tenant-wide at any time.
Short answers for project leads, IT and data protection.
Yes, through a custom connector in Claude that uses the MCP server of WORKSPACE.PM. The person enters the MCP address in Claude and signs in with their WORKSPACE.PM account. This works in Claude on the web, in Claude Desktop and in Cowork, on every plan from Free to Enterprise.
On the WORKSPACE.PM side, MCP access is part of every tenant, without an add-on licence and without an AI provider of your own. On the Anthropic side, a custom connector is according to the documentation included in the free plan as well, limited to one connector there; Pro, Max, Team and Enterprise allow several. The usage limits of your Claude plan continue to apply.
Read and, if the role allows it, write: projects, portfolios and scenarios, risks with measures, Kanban cards, time entries, resource assignments, OKRs, requirements, lessons learned and more, over 200 tools in total. Every answer links to the object in WORKSPACE.PM. Not reachable via MCP are meetings, documents, stakeholders, change requests, dashboards and user administration.
No. Each person signs Claude in as themselves, and every call is checked server-side with exactly their rights, including tenant separation in the database. An additional role gate for external AI clients can only narrow these rights further, never widen them.
Yes. Claude shows an approval request before tool calls and lets you choose whether to allow once or always. Anthropic recommends allowing permanently only for tools you trust to run unsupervised. Independently of that, WORKSPACE.PM decides through the role gate whether write access is possible at all, and logs every change with channel MCP.
In WORKSPACE.PM through the tenant-wide MCP switch and the role gate for external AI clients, plus the usage overview with person, requests, last use and client. On Claude Team and Enterprise, additionally only an organisation owner creates the connector; members can then connect to it but cannot create their own.
WORKSPACE.PM sends nothing to Anthropic; Claude retrieves answers, which then become part of your chat history at Anthropic. For Team and Enterprise, Anthropic's commercial terms apply without training on your data. On Free, Pro and Max, training is according to Anthropic on by default and can be turned off in the privacy settings. Check Anthropic's current terms.
WORKSPACE.PM processes project data exclusively in Germany, as SaaS, managed hosting or on-premises. Claude connects from Anthropic's cloud to the endpoint; there is no broker and no additional store. What Anthropic processes from the answer is governed by your contract with Anthropic, not by WORKSPACE.PM.
For WORKSPACE.PM the data processing agreement under Art. 28 GDPR applies that you conclude for the platform anyway. Which optional third-party integrations you activate, and which data is transmitted in the process, is your decision as controller. For Claude your contract with Anthropic applies. Please have the final assessment made by your data protection officer.
Yes. The same MCP endpoint works with every client that speaks Streamable HTTP and OAuth. Microsoft Copilot has its own page, because an agent is built in Copilot Studio there. The overview of all routes is on the page Connect AI assistants.
Thirty minutes with someone who knows the MCP server from the code: identity chain, role gate, audit trail and what your data protection officer will ask.
Product facts as of September 2026, taken from the WORKSPACE.PM source code and tool catalogue. Statements about Claude are based on Anthropic's public documentation as of September 2026. Claude is a trademark of Anthropic, PBC. WORKSPACE.PM is not affiliated with Anthropic.
