Short answer
Which integration paths, MCP capabilities and APIs do enterprise AI platforms provide?
Connectors, MCP and APIs solve different integration problems. ChatGPT Enterprise documents full MCP support as a beta on ChatGPT web with admin and RBAC controls. nuwacom documents more than 100 tool connections, MCP and an API with Completion and Agent endpoints. Microsoft 365 Copilot documents connectors, MCP apps in declarative agents and a dedicated extensibility and API stack. Langdock documents REST, MCP, A2A and provider-compatible Completion endpoints. The deciding factors are not protocol names but permissions, authentication, plan scope, write actions and governance. [20][18][86][31][06][45][23][88][89][14]
Facts from vendor documentation. Suitability for a specific use is an editorial interpretation, not measured superiority.
Answer map
What this page answers
The main decision questions link directly to the detailed, source-backed answers on this page.
Evaluation criteria
4 criteria to evaluate separately
Integrations
Evaluate which systems can connect natively, through APIs or open protocols, and which permissions, approvals and implementation work are required.
API and development
Evaluate API compatibility, model coverage, limits, data regions and cost separately from the normal chat workspace.
Agents and workflows
Evaluate which agents and workflows can execute tasks, which triggers and tool actions are available, and how approvals, failures and human oversight are handled.
Company knowledge
Evaluate which internal sources can be connected, how source permissions are preserved and whether answers can be traced back to evidence.
At a glance
How do the documented offers differ?
| Criterion | ChatGPT Enterprise | nuwacom | Microsoft 365 Copilot | Langdock |
|---|---|---|---|---|
| Integrations | ChatGPT Enterprise: administered apps and MCP support in beta. [20][18][86] OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review. | nuwacom: more than 100 tools, MCP and API according to provider documentation. [31][06][45] Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case. | Microsoft 365 Copilot: connectors, agents and MCP apps. [23][88][89] MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope. | Langdock: integrations and open interfaces. [14] An interface does not establish the exact connector, write permissions or implementation effort. |
| API and development | ChatGPT Enterprise: assess the API platform separately. [20] A ChatGPT Enterprise licence does not establish included general API quotas. Check the contract scope. | nuwacom: documented API with Completion and Agent endpoints. [31][45] Authentication, endpoint availability, limits, plan scope and draft/publish behaviour must be checked for the intended production use. | Microsoft 365 Copilot: dedicated extensibility and API stack. [87][89] A Microsoft 365 Copilot user licence does not automatically establish access to every API, agent or Copilot Studio capability. Licence, development environment, tenant settings and any usage-based billing must be assessed separately. | Langdock: publicly documented multi-provider API. [15] Supported models, regions and rate limits depend on endpoint and workspace. |
| Agents and workflows | ChatGPT Enterprise: agents and administered tool actions. [18][20][86] The documented MCP write actions are beta and do not establish a scheduled, continuously running business process. Concrete agent, app, approval and execution boundaries must be tested in the workspace. | nuwacom: Agents and Workflows with logic, approvals and scheduling. [37][39] The Agent Actions described on the facts page are marked as Beta. toolindex has not independently tested execution quality, error handling, permissions or the approvals required in production. | Microsoft 365 Copilot: agents with licence-dependent extensibility. [23][26][87][89] Agent authoring, grounding on organizational data and enhanced capabilities can require a Microsoft 365 Copilot licence, Copilot Studio or pay-as-you-go billing. Admin settings can impose additional limits. | Langdock: agents and multi-step workflows. [16][17][13] Workflow execution and model usage are separate cost drivers. An agent feature is not proof that a business process will succeed. |
| Company knowledge | ChatGPT Enterprise: approved company sources and files. [18][20] Availability and permissions depend on apps, admin approval and workspace configuration. toolindex has not run a retrieval benchmark. | nuwacom: shared Context Engine across several platform components. [33][31] toolindex has not hands-on tested retrieval quality, update speed or permission propagation. | Microsoft 365 Copilot: Microsoft Graph and work context. [23][26] Copilot Chat without the relevant licence scope is not equivalent to automatic access to all company data. | Langdock: Knowledge Bases with API access. [11] Search retrieves relevant passages rather than automatically sending every document to a model. toolindex has not benchmarked answer quality. |
Vendor claims, not measurements from a product test. Limitations are shown in each cell. The sections below explain the decision context.
Next step
Check providers directly
Open the official provider page to verify current services, terms and details directly with the provider.
Decision guide · Decision context
How do connectors, MCP and APIs differ in enterprise AI?
A packaged connector typically links a specific business system through a predefined permission and data model. MCP standardizes how tools and context are exposed to compatible AI hosts, while an API enables custom software integration at endpoint level. The same platform can offer all three paths with different authentication, administration, write and plan boundaries. The integration path should therefore be evaluated per use case rather than as a feature checkbox. [20][18][86][31][06][45][23][88][89][87][14][15]
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
OpenAI separates its ChatGPT business offers from the API platform used for custom software integrations. [20]
Interpretation and limitation: A ChatGPT Enterprise licence does not establish included general API quotas. Check the contract scope.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
The nuwacom Platform provides an API with API keys. The current OpenAPI specification documents model and asset endpoints, an OpenAI-compatible Chat Completion endpoint, and endpoints to list, create, update and publish Agents. [31][45]
Interpretation and limitation: Authentication, endpoint availability, limits, plan scope and draft/publish behaviour must be checked for the intended production use.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
Microsoft documents a dedicated Microsoft 365 Copilot extensibility stack with agents, connectors, plugins, Microsoft 365 Copilot APIs and developer tools. These developer paths should be separated from standard Copilot use inside Office applications. [87][89]
Interpretation and limitation: A Microsoft 365 Copilot user licence does not automatically establish access to every API, agent or Copilot Studio capability. Licence, development environment, tenant settings and any usage-based billing must be assessed separately.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Langdock documents provider-compatible completion endpoints for OpenAI, Anthropic, Google and Mistral models under one Langdock API key. [15]
Interpretation and limitation: Supported models, regions and rate limits depend on endpoint and workspace.
Source checked: · Not hands-on tested
Decision guide · Decision context
What MCP product scope do the four enterprise AI platforms document?
OpenAI documents full MCP for ChatGPT Enterprise and Edu on ChatGPT web as a beta, including administered write and modify actions. nuwacom documents MCP server connections and MCP clients as a tool context in its current OpenAPI. Microsoft documents MCP apps as MCP server-based actions in declarative agents inside Microsoft 365 Copilot. Langdock lists MCP alongside REST and A2A as an integration path. These statements are not equivalent: plan, host, admin approval, authentication and allowed actions differ. [20][18][86][31][06][45][23][88][89][14]
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Decision guide · Decision context
How do the documented API paths differ?
OpenAI treats the API platform separately from ChatGPT Enterprise, and an Enterprise licence does not establish general API quota. nuwacom publishes an OpenAPI specification with model, asset, Completion and Agent endpoints. Microsoft describes Microsoft 365 Copilot APIs as part of a broader extensibility stack. Langdock documents provider-compatible Completion endpoints under one Langdock API key. Authentication, rate limits, model coverage, data region, cost and support should be checked separately for each API. [20][31][45][87][89][15]
OpenAI separates its ChatGPT business offers from the API platform used for custom software integrations. [20]
Interpretation and limitation: A ChatGPT Enterprise licence does not establish included general API quotas. Check the contract scope.
Source checked: · Not hands-on tested
The nuwacom Platform provides an API with API keys. The current OpenAPI specification documents model and asset endpoints, an OpenAI-compatible Chat Completion endpoint, and endpoints to list, create, update and publish Agents. [31][45]
Interpretation and limitation: Authentication, endpoint availability, limits, plan scope and draft/publish behaviour must be checked for the intended production use.
Source checked: · Not hands-on tested
Microsoft documents a dedicated Microsoft 365 Copilot extensibility stack with agents, connectors, plugins, Microsoft 365 Copilot APIs and developer tools. These developer paths should be separated from standard Copilot use inside Office applications. [87][89]
Interpretation and limitation: A Microsoft 365 Copilot user licence does not automatically establish access to every API, agent or Copilot Studio capability. Licence, development environment, tenant settings and any usage-based billing must be assessed separately.
Source checked: · Not hands-on tested
Langdock documents provider-compatible completion endpoints for OpenAI, Anthropic, Google and Mistral models under one Langdock API key. [15]
Interpretation and limitation: Supported models, regions and rate limits depend on endpoint and workspace.
Source checked: · Not hands-on tested
Decision guide · Decision context
What should be checked for read and write tool actions?
Reading, searching and writing are different risk classes. For write actions, organizations should also establish who approves the tool, which users or agents may execute it, whether confirmations are required, which parameters can be fixed in advance and how changes are logged. Two platforms can support the same protocol while exposing very different action and governance boundaries. [20][18][86][31][06][45][37][39][23][88][89][26][87][14][16][17][13]
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
OpenAI describes agents and approved tools for ChatGPT Enterprise. After administrative approval, MCP-powered apps can also perform write and modify actions and trigger tasks in connected systems. [18][20][86]
Interpretation and limitation: The documented MCP write actions are beta and do not establish a scheduled, continuously running business process. Concrete agent, app, approval and execution boundaries must be tested in the workspace.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
nuwacom documents AI Agents for multi-step tasks and Workflows with triggers, action nodes, logic controls, Agents, integrations and optional manual approvals. Workflows can be scheduled. [37][39]
Interpretation and limitation: The Agent Actions described on the facts page are marked as Beta. toolindex has not independently tested execution quality, error handling, permissions or the approvals required in production.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
Microsoft 365 Copilot supports declarative and other agent paths. Microsoft also documents Copilot Studio for custom agents and actions; the available scope depends on licensing, billing model and tenant configuration. [23][26][87][89]
Interpretation and limitation: Agent authoring, grounding on organizational data and enhanced capabilities can require a Microsoft 365 Copilot licence, Copilot Studio or pay-as-you-go billing. Admin settings can impose additional limits.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Langdock documents agents and workflows that combine agents, integrations and logic into multi-step processes. [16][17][13]
Interpretation and limitation: Workflow execution and model usage are separate cost drivers. An agent feature is not proof that a business process will succeed.
Source checked: · Not hands-on tested
Decision guide · Decision context
How do integrations and company knowledge relate?
Integrations can expose company knowledge as well as enable actions. For RAG and knowledge use cases, a connector statement is therefore not enough: permission inheritance, freshness, search or indexing logic, source attribution and the separation between read-only knowledge and write-capable tools matter. This connects the integration decision to the separately documented RAG and governance evaluation. [18][20][86][33][31][06][45][23][26][88][89][11][14]
According to OpenAI, ChatGPT Enterprise can use approved company sources, tools and files. [18][20]
Interpretation and limitation: Availability and permissions depend on apps, admin approval and workspace configuration. toolindex has not run a retrieval benchmark.
Source checked: · Not hands-on tested
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
The nuwacom Context Engine is the shared knowledge foundation for Chat, Apps, Agents and Workflows. Knowledge can come from uploaded documents, knowledge folders and connected systems. Answers can identify the sources used. [33][31]
Interpretation and limitation: toolindex has not hands-on tested retrieval quality, update speed or permission propagation.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
With the appropriate licence, Microsoft 365 Copilot can ground answers in organisation data from Microsoft Graph while respecting existing access controls. [23][26]
Interpretation and limitation: Copilot Chat without the relevant licence scope is not equivalent to automatic access to all company data.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
Langdock documents Knowledge Bases for searching document collections and using them in chat, agents, workflows and through the Knowledge Folder API. [11]
Interpretation and limitation: Search retrieves relevant passages rather than automatically sending every document to a model. toolindex has not benchmarked answer quality.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Decision guide · Decision context
Which plan, admin and security boundaries belong in an integration comparison?
Before comparing products, teams should record which product and plan contains each required integration, who can enable it, which authentication method is used, which data can leave the platform context, which actions are permitted and whether separate developer or usage billing applies. Especially for MCP and agents, a general vendor capability is not a substitute for the exact product and tenant scope. [20][18][86][22][31][06][45][03][23][88][89][25][14][12][13]
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
ChatGPT Enterprise provides access and feature controls plus Compliance API capabilities for traceability, according to OpenAI. [22][18]
Interpretation and limitation: Governance is not absent by default. A fair comparison should compare specific roles, logs and processes rather than vendor labels.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
nuwacom documents central governance for user groups, roles, model enablement, Workspaces, Connectors, Guardrails, approvals and logging. [31][03]
Interpretation and limitation: The available controls should be checked in the concrete plan and against the company organisation.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
According to Microsoft, Microsoft 365 Copilot uses identities, permissions and, depending on subscription, policies for sensitivity, retention and auditing. [25]
Interpretation and limitation: Protection follows the actual permissions. Over-broad source access is not automatically fixed by AI.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Langdock documents workspace permissions and offers separate agent governance for reviewing and approving agents. [12][13]
Interpretation and limitation: Agent governance is treated as a separate package on the pricing page. Scope and future cost should be checked separately.
Source checked: · Not hands-on tested
Decision guide · Decision context
How should an integration and API pilot be designed?
An integration pilot should test the same business operation across candidates and do more than establish a technical connection. Authentication, permissions, data path, response or action latency, failure cases, logging and change effort should be recorded. APIs add rate limits, versioning and cost; MCP testing should also version tool definitions and administrative approvals.
- Define the same read and write use case for each candidate.
- Document authentication, user permissions and admin approval.
- Record the data path and third parties used by each connection.
- Test failures, timeouts, permission withdrawal and changed tool definitions.
- Track API limits, versioning and cost separately.
- Confirm product, plan and tenant prerequisites before approval.
Decision guide · Decision context
Which AI software can connect to existing enterprise systems and data sources?
All four compared enterprise AI platforms document integration paths, but connectors, APIs, MCP and embedded extensions are different mechanisms. Selection should verify which concrete systems can be connected, how authentication works and whether a connection only reads or can also execute actions. [20][18][86][31][06][45][23][88][89][87][14][15]
ChatGPT Enterprise supports administratively controlled apps and sources. OpenAI also documents full MCP support, including write and modify actions, as a beta for ChatGPT Enterprise and Edu on ChatGPT web. [20][18][86]
Interpretation and limitation: OpenAI describes full MCP as a beta on ChatGPT web. Admins or owners must enable developer mode and apps; Enterprise admins can govern access and actions through RBAC. External MCP servers and their data flows require separate review.
Source checked: · Not hands-on tested
OpenAI separates its ChatGPT business offers from the API platform used for custom software integrations. [20]
Interpretation and limitation: A ChatGPT Enterprise licence does not establish included general API quotas. Check the contract scope.
Source checked: · Not hands-on tested
nuwacom describes compatibility with more than 100 tools, including Microsoft 365, SharePoint, OneDrive, Outlook, Google Drive, Slack and Confluence. MCP servers and the nuwacom API can also be connected; the current OpenAPI specification also exposes MCP clients as a tool context for Agent Actions. [31][06][45]
Interpretation and limitation: Compatibility does not mean identical read, write or sync permissions. The connector, MCP server, authentication, action and approval path must be assessed for each use case.
Source checked: · Not hands-on tested
The nuwacom Platform provides an API with API keys. The current OpenAPI specification documents model and asset endpoints, an OpenAI-compatible Chat Completion endpoint, and endpoints to list, create, update and publish Agents. [31][45]
Interpretation and limitation: Authentication, endpoint availability, limits, plan scope and draft/publish behaviour must be checked for the intended production use.
Source checked: · Not hands-on tested
Microsoft 365 Copilot is embedded in Microsoft 365 applications and can be extended through Copilot connectors and agents. Microsoft explicitly documents MCP apps as MCP server-based actions in declarative agents that run inside Microsoft 365 Copilot. [23][88][89]
Interpretation and limitation: MCP apps are an extensibility path through declarative agents, not a universal entitlement of every Microsoft 365 user licence. Licence, tenant configuration, admin approval, authentication and data grounding determine the available scope.
Source checked: · Not hands-on tested
Microsoft documents a dedicated Microsoft 365 Copilot extensibility stack with agents, connectors, plugins, Microsoft 365 Copilot APIs and developer tools. These developer paths should be separated from standard Copilot use inside Office applications. [87][89]
Interpretation and limitation: A Microsoft 365 Copilot user licence does not automatically establish access to every API, agent or Copilot Studio capability. Licence, development environment, tenant settings and any usage-based billing must be assessed separately.
Source checked: · Not hands-on tested
Langdock describes integrations plus REST, MCP and A2A as ways to connect internal systems and tools. [14]
Interpretation and limitation: An interface does not establish the exact connector, write permissions or implementation effort.
Source checked: · Not hands-on tested
Langdock documents provider-compatible completion endpoints for OpenAI, Anthropic, Google and Mistral models under one Langdock API key. [15]
Interpretation and limitation: Supported models, regions and rate limits depend on endpoint and workspace.
Source checked: · Not hands-on tested
Evidence
Sources and research limits
24 sources used on this page. Checked means that a public source was read. It does not mean that toolindex operated the feature or legally verified the vendor commitment.
- 03nuwacom: AI Governance
· Vendor source
Reviewed area: Roles, permissions, audit logs; preserve source permissions
- 06nuwacom: Connectors
· Vendor source
Reviewed area: Apps; MCP servers; authentication; sharing connectors
- 11Langdock: Knowledge bases
· Vendor source
Reviewed area: Search, document retrieval and Knowledge Folder API
- 12Langdock: Privacy & Security
· Vendor source
Reviewed area: EU application/most models; no training; permissions; deployment
- 13Langdock: Pricing
· Vendor source
Reviewed area: Chat & Agents; Workflows; Governance; API; adjustable selector
- 14Langdock: Enterprise
· Vendor source
Reviewed area: Interoperability; REST, MCP, A2A; custom infrastructure
- 15Langdock: Completion API Overview
· Vendor source
Reviewed area: Provider-compatible endpoints; supported regions; rate limits
- 16Langdock: Introduction to Agents
· Vendor source
Reviewed area: Agents for tasks; sharing and configuration
- 17Langdock: Introduction to Workflows
· Vendor source
Reviewed area: Agents, integrations and logic in multi-step automations
- 18OpenAI: ChatGPT Enterprise
· Vendor source
Reviewed area: Enterprise models/agents; connected tools; governance; contact sales
- 20OpenAI: Enterprise privacy
· Vendor source
Reviewed area: SAML SSO; internal sources; retention; GPTs; API platform
- 22OpenAI: Compliance and administrative tools
· Vendor source
Reviewed area: Compliance API and administrative integrations
- 23Microsoft: Microsoft Copilot overview
· Vendor source
Reviewed area: Basic/Premium distinction; Microsoft 365 apps; Graph; model choice
- 25Microsoft: Enterprise data protection
· Vendor source
Reviewed area: DPA; no foundation-model training; permissions; web search and model exceptions
- 26Microsoft: License options for Microsoft Copilot
· Vendor source
Reviewed area: Add-on subscription prerequisites; work vs web-based chat
- 31nuwacom: nuwacom Platform: Facts and classification
· Vendor source
Reviewed area: FAQ, platform summary, security, API and deployment models
- 33nuwacom: nuwacom Context Engine: Facts and classification
· Vendor source
Reviewed area: FAQ on knowledge sources, permissions, updates and citations
- 37nuwacom: nuwacom AI Agents: Facts and classification
· Vendor source
Reviewed area: Agents: multi-step tasks, knowledge, tool actions marked Beta, model selection and external embedding
- 39nuwacom: nuwacom Workflows: Facts and classification
· Vendor source
Reviewed area: Workflows: triggers, action nodes, logic, Agents, integrations, manual approvals, testing and scheduling
- 45nuwacom: OpenAPI-Spezifikation
· Vendor source
Reviewed area: OpenAPI: Modelle, Assets, OpenAI-kompatible Chat Completions, Agent-Endpunkte, Skills sowie Integrations- und MCP-Actions
- 86OpenAI: Developer mode and MCP apps in ChatGPT
· Vendor source
Reviewed area: Full MCP support is beta for ChatGPT Business, Enterprise and Edu on ChatGPT web; admin enablement and publishing; Enterprise/Edu RBAC; write/modify actions and action controls
- 87Microsoft: Microsoft 365 Copilot extensibility documentation
· Vendor source
Reviewed area: Microsoft 365 Copilot extensibility options include agents, connectors, plugins, Copilot APIs and developer tools
- 88Microsoft: Add MCP apps to declarative agents in Microsoft 365 Copilot
· Vendor source
Reviewed area: MCP apps run inside Microsoft 365 Copilot through declarative agents and MCP server-based actions; remote MCP server and authentication requirements
- 89Microsoft: Set up your development environment to extend Microsoft 365 Copilot
· Vendor source
Reviewed area: Licensing, tenant and admin requirements for Copilot agents; Microsoft 365 Copilot licensed users, pay-as-you-go variants, MCP Apps and organizational-data grounding