Providers
AverQel has two related provider concepts: model providers for AI runtime routing and MCP providers for user-authorized remote tools such as Gmail and GitHub.
Model Providers
OpenRouter, OpenAI-compatible endpoints, Anthropic, Google, Ollama, LM Studio, embeddings, rerankers, and search runtimes power AI generation and retrieval.
Self-hosted SearXNG
DeepSpace can use a configured SearXNG JSON endpoint for server-side web search without a third-party search API key.
MCP Providers
Google Gmail, Drive, Calendar, Chat, People, GitHub, and future approved vendors remain available through the separate MCP surface.
Provider-Owned Login
MCP users authenticate on the provider authorization page. AverQel stores encrypted tokens and safe account identity, not provider passwords.
Explicit Ownership
Provider credentials and MCP connections are scoped to the current tenant and user. They are never treated as a shared global account.
Model providers versus MCP providers
Model providers answer questions or create embeddings. MCP providers remain a separate protected integration surface for external product actions. A Google model provider and a Google Gmail MCP connection are separate integrations with separate credentials, policies, and ownership.
Do not put MCP OAuth credentials into the normal model-provider configuration. MCP uses dedicated provider profiles and dedicated per-user connection records so existing Google, GitHub, Drive, and other integrations remain compatible.
Self-hosted SearXNG web search
Add SearXNG (Self-hosted) from the Web provider tab and enter the URL reachable by the AverQel API, for example http://searxng:8080 when both services share a private Docker network. SearXNG must have its JSON search format enabled. No API key is required.
DeepSpace invokes the bounded web_search tool only when the selected model requests it. Results are fetched server-side, filtered by the configured domain policy, and returned with titles, URLs, snippets, source engines, and available publication dates. The final Markdown response receives a Sources section with links.
Requests use bounded timeouts, Redis-backed per-user rate limits, redirect blocking, URL validation, and endpoint SSRF checks. The model never receives shell or cURL access; it receives only the typed web-search tool and sanitized result data. MCP remains a separate integration surface.
Google and GitHub MCP connections
- AverQel publishes a curated marketplace entry with the official remote endpoint, reviewed tools, requested scopes, and risk policy.
- An administrator configures AverQel's Google or GitHub OAuth client ID, client secret, and exact callback URI on the VPS.
- The user selects Connect and is redirected to Google or GitHub.
- The provider returns an authorization result to AverQel's signed callback.
- AverQel verifies scopes and account identity, encrypts the token material, refreshes the safe catalog, and opens the connection inspector.
- MCP actions remain available only through the current user's approved connection after policy and scope checks pass.
If an OAuth client is not configured, the marketplace entry remains visible but shows Setup pending. This is an operator configuration state, not a request for users to give AverQel their Google or GitHub password.
MCP marketplace trust metadata
- Official: reviewed provider operated by the represented vendor.
- Community: reviewed third-party provider; it is never automatically official.
- New: recently added provider within its catalog review period.
- Trending: reviewed popularity signal with explicit review metadata.
- Interactive: reviewed support for interactive workflows.
These are catalog attributes, not security permissions. Approval status controls whether a provider can be connected; badges help users understand provenance and product status.
Remote MCP transport labels
Remote HTTP means a vendor-hosted HTTPS Streamable HTTP MCP endpoint. Remote SSE means a vendor-hosted HTTPS Server-Sent Events MCP endpoint. AverQel validates remote endpoints and does not let the browser probe them directly.
Stdio, SSH, and local process transports are not supported in this release. AverQel does not clone or execute arbitrary vendor MCP repositories on the VPS. This reduces supply-chain and host-execution risk while the product focuses on approved remote services.
Provider health and catalog preview
Marketplace previews are reviewed metadata. Once connected, AverQel can refresh the live tool catalog and records a safe catalog revision and health status. Health is an operational signal, not an uptime guarantee, and remote providers can change tools or permissions.
The runtime rejects stale catalogs, disabled providers, revoked connections, removed tools, and policy violations. The frontend receives only typed safe DTOs; provider tokens, client secrets, raw OAuth metadata, and raw MCP event payloads remain server-side.
Why AverQel does not clone MCP repositories
The vendor owns its MCP implementation, endpoint availability, OAuth application, and tool behavior. AverQel owns the marketplace review, tenant/user connection, encryption, policy, approval, runtime routing, and safe inspection. Keeping those responsibilities separate makes provider updates safer and prevents unreviewed code from running inside AverQel.
Existing AI provider support
- Chat runtimes include OpenRouter, OpenAI-compatible providers, Anthropic, Google, Ollama, LM Studio, and OpenCode Zen.
- Embedding runtimes include local deterministic paths, sentence-transformers, OpenRouter, Ollama, LM Studio, and OpenAI-compatible providers.
- Reranking and web search use their own provider routing and secret boundaries.
These model-provider flows remain separate from the remote MCP marketplace and are not replaced by it.