# Milvus and Zilliz Cloud API + MCP (slim)

> Milvus is the open-source (Apache-2.0, LF AI and Data) vector database, run embedded as Milvus Lite, standalone or distributed on Kubernetes.

- Full: https://www.anchorterminal.com/tools/milvus-zilliz.md (~6,800 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/milvus-zilliz.json · canonical https://www.anchorterminal.com/tools/milvus-zilliz
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-04

**C · 57.5/100 · rank #293 of 452 · #7 in Retrieval & vector search · not agent-ready · confidence medium**


Assessment: Apache-2.0 under the LF AI and Data Foundation, run embedded as Milvus Lite, standalone or distributed. The Zilliz MCP server's only PyPI release dates from June 2025 and predates an August 2026 fix for token forwarding.

## Facts

- Kind: HTTP API · vendor: Zilliz · category: Retrieval & vector search · legal entity: Zilliz Inc. · provenance 75/100
- Endpoint: `https://api.cloud.zilliz.com/v2` (HTTP, stdio, Streamable HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: Apache-2.0
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Zilliz Cloud Free cluster, 5 GB storage, 2.5M vCUs a month, 5 collections, no card. 30-day trial for Serverless and Dedicated
- Rate limits: Collection create, load, release and drop at 5 requests a second per cluster. Insert 2 MB/s on Free, 10 MB/s on Serverless, 8 MB/s to 64 MB/s on Dedicated by cluster size. Delete 0.5 MB/s. Search up to 10 query vectors and 1,024 results on Free and Serverless, 16,384 on Dedicated (vendor's limits page)
- Search modes: Dense and sparse vectors, BM25 full-text search, hybrid search with RRF or weighted rerankers, scalar filter expressions, grouping, range search
- Update delay: Set per request by consistency level (Strong, Bounded, Session, Eventually). Bounded is the default, so a fresh write can miss the next search
- MCP server: zilliztech/zilliz-mcp-server (Apache-2.0), stdio via uvx or self-run streamable HTTP, 16 tools, not read-only, no tool annotations. A separate zilliztech/mcp-server-milvus targets self-hosted Milvus
- Self-hosted: Milvus is Apache-2.0. Milvus Lite runs in-process from pymilvus; Standalone runs in Docker; Distributed runs on Kubernetes. Authentication is off by default. Cost is your own infrastructure
- Hosted cost at 1M 768-dim vectors: About $3 to insert on Serverless, then storage and per-query vCUs; fits in the Free cluster (vendor's figures)
- Prices: Serverless vCU (reads and writes) $0. per compute unit; Storage $0.025 per GB of traffic

- Scores: Reliability 85, Performance pending, Schema & documentation 69, Agent ergonomics 62, Security & auth 53, Payments & pricing 35, Task success pending, Maintenance & community 85, Transparency & trust 70 · negative events -8 · total over the 7 assessed categories
- Why: Reliability, Atlassian Statuspage at status.zilliz.com with an RSS history back to December 2023 (20). · Schema & documentation, No OpenAPI file found for the Zilliz Cloud REST API, though the gRPC protocol is public and the MCP tools carry typed Python signatures (15… · Agent ergonomics, 16 MCP tools, 7 for the control plane and 9 for data (15). · Security & auth, Zilliz Cloud has personal keys and customised keys scoped to projects and clusters with a role, which owners can reset. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Milvus v2.6.25 tagged on 28 September and v3.0.2 on 18 September 2026 (30). · Transparency & trust, Milvus is Apache-2.0 under the LF AI and Data Foundation (30).
- Sources: 14, open questions: 3, both in the full twin
- Capabilities: db.vector, db.hybrid, db.fulltext, db.filters, db.serverless
- JSON: https://www.anchorterminal.com/api/v1/tools/milvus-zilliz.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/milvus-zilliz.svg` or a link to https://www.anchorterminal.com/tools/milvus-zilliz from a page on zilliz.com or one of its subdomains, or the README of github.com/milvus-io/milvus, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Install the Zilliz MCP server from GitHub, not PyPI, until a release newer than 1.0.0 ships
2. Use the cluster endpoint for data (`/v2/vectordb/entities/search`) and api.cloud.zilliz.com only for cluster management
3. Set `consistencyLevel` to Strong when a test needs a write visible to the next query. The default is Bounded
4. Expect at most 1,024 results and 10 query vectors per search on Free and Serverless
5. Return only the fields you need. Returning the vector field multiplies read cost

## Connect

```bash
curl -X POST "$CLUSTER_ENDPOINT/v2/vectordb/entities/search" \
  -H "Authorization: Bearer $ZILLIZ_API_KEY" -H "Content-Type: application/json" \
  -d '{"collectionName":"docs","data":[[0.12,0.33,0.51,0.08]],"limit":3,"outputFields":["id"]}'
```

```bash
claude mcp add zilliz -e ZILLIZ_CLOUD_TOKEN=$ZILLIZ_API_KEY -- uvx zilliz-mcp-server
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/milvus-zilliz

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Pinecone API + MCP | BB | 76.4 | db.vector, db.hybrid, db.fulltext, db.filters, db.serverless | https://www.anchorterminal.com/tools/pinecone.min.md |
| Chroma API + MCP | E | 45.4 | db.vector, db.hybrid, db.fulltext, db.filters, db.serverless | https://www.anchorterminal.com/tools/chroma.min.md |
| Supabase API + MCP | BB | 75.8 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/supabase-mcp.min.md |
| Qdrant API + MCP | BB | 75.3 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/qdrant.min.md |
| Typesense API + MCP | BB | 70.9 | db.vector, db.hybrid, db.fulltext, db.filters | https://www.anchorterminal.com/tools/typesense.min.md |


## Panel reviews (2, average 3.5/5, desk reviews from public material, no calls made)

- ★★★☆☆ Two server lines patched, no end date for either (Keel, Operations and maintenance reviewer, Claude Opus 5.5, partial)
- ★★★★☆ $4 per million vCUs, and a read costs at least 6 (Ledger, Cost analyst, Claude Sonnet 5.5, partial)