Plugin Engine vs Perspective AI MCP
A side-by-side look at the Plugin Engine and Perspective AI MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Plugin Engine for conversational ai work as a local process; choose Perspective AI MCP for conversational ai over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Plugin Engine when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: API key required.
- You have the keys it needs:
COGNIGY_API_BASE_URL, COGNIGY_API_KEY. - You want tools like
create_ai_agent, update_ai_agent, setup_llm.
Choose Perspective AI MCP when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a remote HTTP/SSE transport.
- Its auth model fits you: OAuth 2.0.
- You want tools like
workspace_list, workspace_get, workspace_get_default.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 61/100 · Good | 59/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | API key required | OAuth 2.0 |
| Pricing | BYOK (pay the provider) | Not declared |
| Required env vars | COGNIGY_API_BASE_URLCOGNIGY_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 18 | 5 |
| Directory activity | 0 views 0 installs 0 upvotes | 3 views 0 installs 0 upvotes |
| Tools | 18 | 22 |
| Full listing | View Plugin Engine | View Perspective AI MCP |
Tools & capabilities
Plugin Engine tools 18
create_ai_agentCreate a complete AI Agent with auto-provisioned flow, job node, and REST endpointupdate_ai_agentUpdate persona, guardrails, job config (role, procedures, LLM, temperature)setup_llmCreate an LLM resource (GPT-4, Claude, Mistral, etc.) with automatic connection validationtalk_to_agentSend a message to an AI Agent and get its response (uses Endpoint Test Mode, so it is not counted as billable)list_resourcesList projects, agents, flows, endpoints, LLMs, knowledge stores, and moreget_resourceGet detailed information about a single resourcedelete_resourcePermanently delete a resourcemanage_knowledgeCreate knowledge stores, add sources (URL, text, file), list chunks for RAGcreate_toolAdd a tool (HTTP, knowledge, email, MCP, A2A) to an agent's job nodeupdate_toolUpdate an existing tool node's configurationmanage_webchatCreate or configure a Webchat v3 endpoint for website deploymentmanage_flow_nodesCreate, update, delete, or list flow nodes for conversation logic- +6 more on the listing page
Perspective AI MCP tools 22
workspace_listList all workspaces you can accessworkspace_getGet details for a workspaceworkspace_get_defaultGet your default workspaceperspective_listList perspectives in a workspace, or search by name across all workspacesperspective_getGet full configuration and stats for a perspectiveperspective_createCreate a new perspective from a natural-language briefperspective_respondAnswer a follow-up question during perspective designperspective_updateRefine a perspective with natural-language feedbackperspective_await_jobLong-poll a perspective design job to completionperspective_get_preview_linkGet a shareable preview URL for testing before deploymentperspective_get_embed_optionsGet embed snippets (fullpage, widget, popup, slider, float, card) and the SDK referenceparticipant_inviteCreate 48-hour magic-link invites, optionally sent via email- +10 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Plugin Engine
{
"mcpServers": {
"cognigy-plugin-engine": {
"command": "npx",
"args": [
"-y",
"-p",
"@cognigy/plugin-engine@latest",
"cognigy-setup"
],
"env": {
"COGNIGY_API_BASE_URL": "YOUR_COGNIGY_API_BASE_URL_HERE",
"COGNIGY_API_KEY": "YOUR_COGNIGY_API_KEY_HERE"
}
}
}
}
Perspective AI MCP
{
"mcpServers": {
"perspective-ai-mcp": {
"url": "https://getperspective.ai/mcp"
}
}
}
Frequently asked questions
Plugin Engine is categorized under Conversational AI and uses a local stdio subprocess. Perspective AI MCP belongs to Conversational AI and uses a remote HTTP/SSE transport. Pick Plugin Engine for conversational ai work and Perspective AI MCP for conversational ai.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Plugin Engine is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Perspective AI MCP has no declared pricing — check the project's own site. Auth: oauth 2.0. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add cognigy-plugin-engine and perspective-ai-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Plugin Engine has a quality signal of 61/100 (Good) with 0 views, 0 installs and 18 GitHub stars. Perspective AI MCP has 59/100 (Good) with 3 views, 0 installs and 5 GitHub stars.