Vectros Ai MCP Server - install, status & alternatives [2026]

01 · Install Vectros Ai MCP Server

before you install - you'll need

Set VECTROS_API_KEY, VECTROS_BOOTSTRAP_TOKEN, VECTROS_MCP_HTTP_PORT, VECTROS_MCP_HTTP_BEARER_TOKEN, VECTROS_API_BASE_URL before connecting.

Claude Code

claude mcp add vectros-ai-vectros-mcp-server -- npx -y @vectros-ai/mcp-server

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "vectros-ai-vectros-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@vectros-ai/mcp-server"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license Apache-2.0 - declared in the repository

npm package @vectros-ai/mcp-server - published under the repo owner's npm scope (@vectros-ai)

registry namespace io.github.vectros-ai is GitHub-verified and matches the repo owner

03 · What Vectros Ai MCP Server can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can ask a question grounded against a single document. Same aggregation + progress-notification shape as rag_ask, fetch one record by id, including its full payload (large payloads truncated to protect the agent context window), create a record of a given type, and patch a record's payload (deep-merged.

Capability map

Tools grouped from the project's README - what Vectros Ai MCP Server lets an agent do.

Record

7 tools - e.g. Query records by lookup field - equality (value), range, or prefix, with asc/desc ordering and an optional sortFrom/sortTo window - or list mode, choosing one o; Fetch one record by id, including its full…

record_query · record_get · record_batch_get · record_create · record_batch_write · record_update…

Document

6 tools - e.g. Ask a question grounded against a single document. Same aggregation + progress-notification shape as rag_ask.; Create a document - inline text body OR local file upload (file mode is stdio-transport…

document_ask · document_ingest · document_query · document_get · document_update · document_delete

Folder

4 tools - e.g. Get a folder by id, or list folders (a parent's children for tree navigation, or a flat tenant list; paginated via nextCursor).; Create a folder.; Update a folder's name / description / ownership…

folder_query · folder_create · folder_update · folder_delete

read & search

2 tools - e.g. List the record-schema catalog the credential can see (filter by surface or resolve one by recordType). Makes record_query / record_create discoverable.; Resolve a user, or an identity entity in a…

list_schemas · lookup_principal

Hybrid

1 tool - e.g. Hybrid BM25 + dense search across the tenant's indexed content (records + documents). Narrow by ownership (scope for one dimension, scopeFilters for several at

hybrid_search

Rag

1 tool - e.g. Ask a question grounded against the indexed corpus. Scope retrieval (ownership - scope or multi-dimension scopeFilters - / folder / type / metadata filters / da

rag_ask

Current

1 tool - e.g. Describe the credential: tenantId, environment, principalType, principalKeyId, principalLabel, and (for scoped credentials) allowedActions + dataScope. Does not

current_identity

Version

1 tool - e.g. Read the audit/version trail (CREATE/UPDATE/DELETE, with actor + diff) for one record or document. Read-only.

version_history

Latest releases

v0.17.0 · 2026-09-08

Vectros MCP server v0.17.0 - Claude Desktop one-click install. Download vectros.mcpb and open it in Claude Desktop (Settings → Extensions), then add your Vectros API key (or run npx -y @vectros-ai/cli bootstrap).

v0.16.1 · 2026-08-30

Vectros MCP server v0.16.1 - Claude Desktop one-click install. Download vectros.mcpb and open it in Claude Desktop (Settings → Extensions), then add your Vectros API key (or run npx -y @vectros-ai/cli bootstrap).

v0.16.0 · 2026-08-27

Vectros MCP server v0.16.0 - Claude Desktop one-click install. Download vectros.mcpb and open it in Claude Desktop (Settings → Extensions), then add your Vectros API key (or run npx -y @vectros-ai/cli bootstrap).

04 · Who maintains Vectros Ai MCP Server

mcp-server is maintained by vectros-ai. It's the only MCP server we track from this author; the repo dates to May 2026.

05 · Facts

repository: github.com/vectros-ai/vectros-mcp-server
website: https://vectros.ai/
category: documentation - ranked #66 of 208 actively-maintained documentation servers as of 2026-09-18.
release cadence: 10+ releases in the last 90 days (latest 2026-09-08)
registry: io.github.vectros-ai/mcp-server (active, first published 2026-06-27 · 14 versions)
packages: npm:@vectros-ai/mcp-server

06 · Vectros Ai MCP Server FAQ

Is Vectros Ai MCP Server still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-08 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

What can Vectros Ai MCP Server do?

With this server connected, an agent can ask a question grounded against a single document. Same aggregation + progress-notification shape as rag_ask, fetch one record by id, including its full payload (large payloads truncated to protect the agent context window), create a record of a given type, and patch a record's payload (deep-merged.

How do I install Vectros Ai MCP Server?

Run `npx -y @vectros-ai/mcp-server`. The README documents 5 environment variables (VECTROS_API_KEY, VECTROS_BOOTSTRAP_TOKEN, VECTROS_MCP_HTTP_PORT…) to set first. Set VECTROS_API_KEY, VECTROS_BOOTSTRAP_TOKEN, VECTROS_MCP_HTTP_PORT, VECTROS_MCP_HTTP_BEARER_TOKEN, VECTROS_API_BASE_URL before connecting. You can also paste the ready-made client config above.

Does Vectros Ai MCP Server run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Vectros Ai MCP Server

Alternatives to Vectros Ai MCP Server

Maintained documentation servers if Vectros Ai MCP Server isn't the fit.

Pairs well with

Servers that cover what Vectros Ai MCP Server doesn't - only shown when the pairing reason fits the companion.

More documentation MCP servers · Vercel MCP · Inkwell · Agent Base · Outline MCP Server · Vouch

More TypeScript MCP servers · Memento · Publishready · Next Devtools MCP · LLM CLI Gateway · Auto Mem · see all