{ "data": { "a": { "slug": "elasticsearch", "name": "Elasticsearch", "vendor": "Elastic", "vendorUrl": "https://www.elastic.co", "kind": "http-api", "category": "vector-search", "summary": "Elasticsearch is Elastic's search engine and vector database, with keyword, vector and hybrid search over a REST API. Agents reach it through that API or the Agent Builder MCP server on Elastic Cloud and Elastic Stack 9.2 or later.", "url": "https://www.anchorterminal.com/tools/elasticsearch", "markdownUrl": "https://www.anchorterminal.com/tools/elasticsearch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/elasticsearch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/elasticsearch.json", "repo": "https://github.com/elastic/elasticsearch", "license": "AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms", "transports": [ "http" ], "packages": [ { "registry": "npm", "name": "@elastic/elasticsearch" }, { "registry": "pypi", "name": "elasticsearch" } ], "auth": "mixed", "authNotes": "Self-serve. The REST API takes `Authorization: ApiKey \u003ckey\u003e`, with keys created in Kibana or by `POST /_security/api_key` and limited by role descriptors and an expiry. The Agent Builder MCP server takes the same kind of key, which needs the `feature_agentBuilder.read` Kibana privilege, or OAuth 2.1 on Serverless projects, where a registered client and a browser consent give each user a revocable connection.", "pricing": "usage", "pricingNotes": "Serverless bills by use, with search from $0.09 a VCU-hour, ingest from $0.14, storage from $0.047 a GB a month and egress from $0.05 a GB. Agent Builder has 1,000 free executions a month, then from $0.025 each. A 14-day Elastic Cloud trial needs no credit card. Self-managed Elasticsearch is free to run under its source licences (https://www.elastic.co/pricing/serverless-search, checked 2026-10-08).", "priceSummary": "$0.09 / unit", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the Serverless OpenAPI file or the pricing page (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 3136798, "pypiWeekly": 7755257, "asOf": "2026-10-08" }, "docsUrl": "https://www.elastic.co/docs/solutions/search", "llmsTxt": "https://www.elastic.co/docs/llms.txt", "openapi": "https://www.elastic.co/docs/api/doc/elasticsearch-serverless.json", "capabilities": [ "db.vector", "db.hybrid", "db.fulltext", "db.filters", "db.serverless" ], "tags": [ "hosted", "usage", "free-trial", "no-card", "open-source", "self-hosted", "mcp", "oauth", "openapi", "llms-txt", "typescript", "python", "status-page", "bug-bounty", "soc2", "sla" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 67.7, "grade": "B", "agentReady": false, "rank": 224, "ranked": true, "rankOf": 842, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 77, "maintenance": 83, "payments": 35, "reliability": 62, "schema": 88, "security": 72, "transparency": 71 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": -2, "negativeNotes": [ "Sixteen Elasticsearch security advisories were posted between 25 September and 6 October 2026. The one we read, ESA-2026-199 (CVE-2026-103009, CVSS 7.1), is an authorisation bypass in cross-cluster search on self-managed clusters, fixed in 8.19.23, 9.4.8 and 9.5.5, and Elastic says Serverless is not affected. Fixed and disclosed, so a small deduction (https://discuss.elastic.co/c/announcements/security-announcements/31)." ], "verdict": "Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.", "bestFor": "Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.", "strengths": [ "OpenAPI 3.0.3 file for the Serverless API with 311 operations, plus llms.txt and a Markdown twin of every docs page", "API keys take role descriptors that limit indices and privileges, with an expiry, and the MCP server accepts OAuth 2.1 on Serverless", "Agent Builder MCP server is generally available on Serverless and on Elastic Stack 9.3 and later", "14-day Elastic Cloud trial with no credit card, and unit prices published for Serverless", "Public bug bounty on HackerOne, CVE Numbering Authority status and dated security advisories" ], "weaknesses": [ "More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents", "Elasticsearch 9.5.0 (29 July 2026) returned incorrect results for some `must_not` queries with no error, fixed in 9.5.1 and 9.5.2", "No request rate limit with numbers was found in the reviewed documentation", "The 99.95 per cent Serverless SLA applies only at Platinum or Enterprise subscription level", "The monthly terms forbid use of the cloud service for benchmarking, competitive or comparative purposes", "Search compute on Serverless does not scale to zero, so an idle project is still billed a baseline" ], "agentNotes": [ "Send `Authorization: ApiKey \u003ckey\u003e` to the project's Elasticsearch URL. The MCP server is on the Kibana URL at `/api/agent_builder/mcp`", "Create the MCP key with `feature_agentBuilder.read` and only the index patterns needed, or the endpoint answers 403", "On 429, wait and retry with exponential backoff. Do not set short client timeouts, because a retried request joins the back of the queue", "Page past 10,000 hits with `search_after`, not `from` and `size`", "Tool calls made directly through the Tools API skip Agent Builder's confirmation prompts, so restrict the key instead" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 67.7 } ], "editorialScores": { "ergonomics": 77, "maintenance": 83, "payments": 35, "reliability": 62, "schema": 88, "security": 72, "transparency": 70 }, "provenanceScore": 71 }, "connect": { "install": "npm install @elastic/elasticsearch", "http": "curl -X GET \"${ES_URL}/_cat/indices?v=true\" \\\n -H \"Authorization: ApiKey ${API_KEY}\"", "config": { "mcpServers": { "elastic-agent-builder": { "args": [ "mcp-remote", "${KIBANA_URL}/api/agent_builder/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "command": "npx", "env": { "AUTH_HEADER": "ApiKey ${API_KEY}", "KIBANA_URL": "${KIBANA_URL}" } } } } }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/elasticsearch" }, "area": "developer", "unitPrices": [ { "item": "Serverless search compute, VCU-hour", "unit": "compute-unit", "usd": 0.09, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless ingest compute, VCU-hour", "unit": "compute-unit", "usd": 0.14, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless storage", "unit": "gb-month", "usd": 0.047, "note": "Quoted as a floor on the pricing page" }, { "item": "Serverless egress", "unit": "gb", "usd": 0.05, "note": "Quoted as a floor on the pricing page" }, { "item": "Agent Builder execution", "unit": "call", "usd": 0.025, "note": "After 1,000 free executions a month, quoted as a floor" } ], "provenance": { "legalEntity": "Elasticsearch B.V.", "domain": "elastic.co", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.elastic.co/agreements/cloud-monthly", "privacy": "https://www.elastic.co/legal/product-privacy-statement", "statusPage": "https://status.elastic.co", "changelog": "https://www.elastic.co/docs/release-notes/elasticsearch", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The Cloud Monthly Terms of Service (effective 12 September 2025) name the contracting entity by customer location, Elasticsearch, Inc. for the United States and Elasticsearch B.V. or Elastic International B.V. elsewhere. The page is a cover that links the PDF.", "Customers with an order form are under the Elastic Cloud Service Subscription Agreement of 5 March 2026 at https://www.elastic.co/agreements/global/cloud-services.", "The Product Privacy Statement (7 September 2026) is issued by Elastic N.V. and its subsidiaries and covers Elastic Cloud Hosted, Serverless and self-managed software. The General Privacy Statement covers only websites and events.", "www.elastic.co/.well-known/security.txt returned 404. Reports go to HackerOne or security@elastic.co.", "No RDAP service answered for elastic.co, so the registration date is not recorded.", "Project endpoints are on Elastic Cloud hostnames that we did not call. `endpointOnVendorDomain` rests on the docs, not on a request." ], "score": 71 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/elasticsearch.json", "live": { "slug": "elasticsearch", "vendorStatus": { "page": "https://status.elastic.co", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-10-09T11:39:12.295314988Z" }, "updatedAt": "2026-10-09T11:39:12.295314988Z" } }, "answer": "Qdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing.", "b": { "slug": "qdrant", "name": "Qdrant API + MCP", "vendor": "Qdrant", "vendorUrl": "https://qdrant.tech", "kind": "http-api", "category": "vector-search", "summary": "Open-source vector database written in Rust, run yourself or on Qdrant Cloud.", "url": "https://www.anchorterminal.com/tools/qdrant", "markdownUrl": "https://www.anchorterminal.com/tools/qdrant.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/qdrant.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/qdrant.json", "repo": "https://github.com/qdrant/qdrant", "license": "Apache-2.0", "transports": [ "http", "stdio", "streamable-http" ], "remoteUrl": "https://api.cloud.qdrant.io", "packages": [ { "registry": "pypi", "name": "qdrant-client" }, { "registry": "npm", "name": "@qdrant/js-client-rest" }, { "registry": "pypi", "name": "mcp-server-qdrant" } ], "auth": "api-key", "authNotes": "Cluster requests take a database API key in the `api-key` header or as a Bearer token. Qdrant Cloud keys can be read-only or read-write, limited to chosen collections, and expire after 90 days by default. The Cloud management API at api.cloud.qdrant.io uses separate management keys. The MCP server reads `QDRANT_URL` and `QDRANT_API_KEY`.", "pricing": "freemium", "pricingNotes": "Qdrant Cloud Free is a single-node cluster with 0.5 vCPU, 1 GB RAM and 4 GB disk, no card, suspended after 1 week unused and deleted after 4 weeks. Standard is billed hourly on CPU, memory and disk, with no rate card on the page, only a calculator. Premium has a minimum spend, and Hybrid Cloud and Private Cloud are priced on request. Payment by card or through the AWS, GCP or Azure marketplaces. Self-hosting the Apache-2.0 database is free, you pay for your own servers (https://qdrant.tech/pricing/).", "priceSummary": "Freemium", "where": "both", "x402": { "level": "no", "evidence": "No x402 or per-call payment support in the docs or pricing (checked 2026-09-30).", "endpoints": [] }, "toolCount": 2, "popularity": { "githubStars": 34889, "npmWeekly": 1138118, "pypiWeekly": 2979954, "asOf": "2026-09-30" }, "docsUrl": "https://qdrant.tech/documentation/", "llmsTxt": "https://qdrant.tech/llms.txt", "openapi": "https://raw.githubusercontent.com/qdrant/qdrant/master/docs/redoc/master/openapi.json", "capabilities": [ "db.vector", "db.hybrid", "db.fulltext", "db.filters" ], "tags": [ "open-source", "self-hosted", "local", "hosted", "freemium", "free-tier", "no-card", "mcp", "llms-txt", "openapi", "python", "typescript", "read-only-mode", "enterprise" ], "lastRelease": "2026-09-16", "graded": true, "anchor": { "graded": true, "score": 75.3, "grade": "BB", "agentReady": true, "rank": 50, "ranked": true, "rankOf": 842, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 87, "maintenance": 85, "payments": 30, "reliability": 80, "schema": 87, "security": 83, "transparency": 83 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-01" }, "negative": -2, "negativeNotes": [ "GHSA-f632-vm87-2m2f, high severity, arbitrary file write through the `/logger` endpoint. The fix (\"Restrict /logger API\", #7527) landed on 13 November 2025 and shipped in v1.16.0, and the advisory was published on 5 February 2026. Fixed and disclosed, so a small deduction (https://github.com/qdrant/qdrant/security)." ], "verdict": "Database keys can be read-only, limited to chosen collections and expire after 90 days by default. The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025.", "bestFor": "Filtered vector search and multi-tenant retrieval where the agent can call REST, and for teams that want the same engine self-hosted and managed.", "strengths": [ "Database keys can be read-only, limited to chosen collections and expire after 90 days by default", "429 responses carry `Retry-After` in seconds, and `wait=true` makes writes read-your-own-write", "Published SLAs from 99.5% on Free and Standard to 99.95% with multi-AZ", "OpenAPI file in the repo, llms.txt over 547 Markdown pages, clients in six languages", "Three server releases since July, the latest v1.19.1 on 3 September 2026" ], "weaknesses": [ "The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025", "No per-unit rate card for Qdrant Cloud, only a calculator", "Self-hosted builds send usage statistics by default until you opt out", "474 open issues on the server repo, including a batch of July bug reports", "Keyword search means setting up sparse BM25 vectors, not a plain text query" ], "agentNotes": [ "Create payload indexes on the fields you filter on, or filtered search slows on large collections", "Use `/points/query` with `prefetch` to fuse dense and BM25 results", "Pass `wait=true` on upserts when the next step reads its own writes", "On 429, wait for the `Retry-After` seconds before retrying", "Set `with_vector=false` unless the task needs vectors, since they dominate response size" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 8, "avgRating": 3.6, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "BB", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 75.3 } ], "editorialScores": { "ergonomics": 87, "maintenance": 85, "payments": 30, "reliability": 80, "schema": 87, "security": 83, "transparency": 82 }, "provenanceScore": 83 }, "connect": { "install": "pip install qdrant-client", "http": "curl -s \"$QDRANT_URL/collections\" -H \"api-key: $QDRANT_API_KEY\"", "claudeCode": "claude mcp add qdrant -e QDRANT_URL=$QDRANT_URL -e QDRANT_API_KEY=$QDRANT_API_KEY -e COLLECTION_NAME=agent-memory -- uvx mcp-server-qdrant", "config": { "mcpServers": { "qdrant": { "args": [ "mcp-server-qdrant" ], "command": "uvx", "env": { "COLLECTION_NAME": "agent-memory", "QDRANT_API_KEY": "${QDRANT_API_KEY}", "QDRANT_URL": "${QDRANT_URL}" } } } } }, "letme": { "capability": "https://letme.dev/db.vector", "tool": "https://letme.dev/qdrant" }, "area": "developer", "provenance": { "legalEntity": "Qdrant Solutions GmbH", "domain": "qdrant.tech", "domainRegistered": "2020-10-27", "endpointOnVendorDomain": true, "terms": "https://qdrant.tech/legal/terms_and_conditions/", "privacy": "https://qdrant.tech/legal/privacy-policy/", "statusPage": "https://status.qdrant.io", "changelog": "https://github.com/qdrant/qdrant/releases", "securityTxt": "none", "checked": "2026-09-30", "notes": [ "Cloud clusters and the management API live on qdrant.io, a second Qdrant domain" ], "score": 83 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/qdrant.json", "live": { "slug": "qdrant", "probe": { "target": "https://api.cloud.qdrant.io", "method": "get", "lastAt": "2026-10-09T11:46:38.07930156Z", "lastOk": true, "lastStatus": 404, "lastMs": 266, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 261, "p95ms24h": 353, "samples24h": 259, "samples30d": 2311, "days": [ { "date": "2026-09-30", "probes": 35, "ok": 35 }, { "date": "2026-10-01", "probes": 276, "ok": 276 }, { "date": "2026-10-02", "probes": 248, "ok": 248 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 125, "ok": 125 } ] }, "vendorStatus": { "page": "https://status.qdrant.io", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-09T07:58:27.869101695Z" }, "versions": [ { "registry": "github", "name": "qdrant/qdrant", "version": "v1.19.2", "released": "2026-10-05", "seenAt": "2026-10-08T16:26:46.209708295Z" }, { "registry": "npm", "name": "@qdrant/js-client-rest", "version": "1.19.0", "seenAt": "2026-10-08T16:26:44.272409676Z" }, { "registry": "pypi", "name": "mcp-server-qdrant", "version": "0.8.1", "released": "2025-12-10", "seenAt": "2026-10-08T16:26:45.553672283Z" }, { "registry": "pypi", "name": "qdrant-client", "version": "1.19.1", "released": "2026-09-16", "seenAt": "2026-10-08T16:26:44.125643838Z" } ], "githubStars": 34978, "npmWeekly": 944685, "pypiWeekly": 3116656, "securityTxt": { "url": "https://qdrant.tech/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:59.663461651Z" }, "llmsTxt": { "url": "https://qdrant.tech/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-08T14:00:47.819840781Z" }, "domain": { "domain": "qdrant.tech", "registered": "2020-10-27", "source": "https://rdap.radix.host/rdap/domain/qdrant.tech", "checkedAt": "2026-10-04T13:05:31.30945636Z" }, "pages": [ { "url": "https://qdrant.tech/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-08T18:23:35.458528024Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "1e372d02af67" }, { "url": "https://qdrant.tech/legal/privacy-policy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-08T18:23:31.21027953Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "67688d486a00" }, { "url": "https://qdrant.tech/legal/terms_and_conditions/", "kind": "terms", "status": 200, "checkedAt": "2026-10-08T18:23:33.397271456Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "50f965925025" } ], "updatedAt": "2026-10-09T11:46:38.07930156Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Elastic", "b": "Qdrant", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.cloud.qdrant.io", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, stdio, Streamable HTTP", "name": "Transports" }, { "a": "OAuth or key", "b": "API key", "name": "Auth" }, { "a": "Pay per use", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms", "b": "Apache-2.0", "name": "Licence" }, { "a": "none", "b": "2", "name": "Tools exposed" }, { "a": "no", "b": "yes", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-06", "b": "2026-09-16", "name": "Last release" }, { "a": "couldn't be read", "b": "2021-12-10", "name": "Terms last updated" }, { "a": "2026-09-07", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "3.1M npm/wk, 7.8M PyPI/wk", "b": "35k stars, 1.1M npm/wk, 3M PyPI/wk", "name": "Popularity" }, { "a": "none", "b": "3.6/5 (8)", "name": "Agent reviews" } ], "faq": [ { "answer": "Qdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing.", "question": "Which is better for AI agents, Elasticsearch or Qdrant API + MCP?" }, { "answer": "Elasticsearch takes an API key or an OAuth sign-in. Qdrant API + MCP needs an API key.", "question": "Do Elasticsearch and Qdrant API + MCP need an API key?" }, { "answer": "No hosted endpoint is listed for Elasticsearch. Qdrant API + MCP has a hosted endpoint at https://api.cloud.qdrant.io.", "question": "Can an agent call Elasticsearch and Qdrant API + MCP without installing anything?" }, { "answer": "Yes. Elasticsearch is open source (AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms). Qdrant API + MCP is open source (Apache-2.0).", "question": "Are Elasticsearch and Qdrant API + MCP open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 35 against 30" ], "also": null, "goodFor": "Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.", "slug": "elasticsearch", "watchFor": "More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents" }, { "aheadOn": [ "Reliability, 80 against 62", "Agent ergonomics, 87 against 77", "Security \u0026 auth, 83 against 72", "Transparency \u0026 trust, 83 against 71" ], "also": [ "Agent-ready, a grade of BB or better", "A hosted endpoint, with nothing to install", "Runs on your own machine" ], "goodFor": "Filtered vector search and multi-tenant retrieval where the agent can call REST, and for teams that want the same engine self-hosted and managed.", "slug": "qdrant", "watchFor": "The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025" } ], "job": { "capability": "db.vector", "name": "Db vector" }, "others": [ { "json": "https://www.anchorterminal.com/compare/chroma-vs-elasticsearch.json", "title": "Chroma API + MCP vs Elasticsearch", "url": "https://www.anchorterminal.com/compare/chroma-vs-elasticsearch" }, { "json": "https://www.anchorterminal.com/compare/chroma-vs-qdrant.json", "title": "Chroma API + MCP vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/chroma-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla.json", "title": "Elasticsearch vs Epsilla Vector Database", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-lancedb.json", "title": "Elasticsearch vs LanceDB", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-lancedb" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-milvus-zilliz.json", "title": "Elasticsearch vs Milvus and Zilliz Cloud API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-milvus-zilliz" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone.json", "title": "Elasticsearch vs Pinecone API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-typesense.json", "title": "Elasticsearch vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector.json", "title": "Elasticsearch vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-vespa.json", "title": "Elasticsearch vs Vespa", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate.json", "title": "Elasticsearch vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate" }, { "json": "https://www.anchorterminal.com/compare/epsilla-vs-qdrant.json", "title": "Epsilla Vector Database vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/epsilla-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/lancedb-vs-qdrant.json", "title": "LanceDB vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/lancedb-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/milvus-zilliz-vs-qdrant.json", "title": "Milvus and Zilliz Cloud API + MCP vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/milvus-zilliz-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/pinecone-vs-qdrant.json", "title": "Pinecone API + MCP vs Qdrant API + MCP", "url": "https://www.anchorterminal.com/compare/pinecone-vs-qdrant" }, { "json": "https://www.anchorterminal.com/compare/qdrant-vs-typesense.json", "title": "Qdrant API + MCP vs Typesense API + MCP", "url": "https://www.anchorterminal.com/compare/qdrant-vs-typesense" }, { "json": "https://www.anchorterminal.com/compare/qdrant-vs-upstash-vector.json", "title": "Qdrant API + MCP vs Upstash Vector API + MCP", "url": "https://www.anchorterminal.com/compare/qdrant-vs-upstash-vector" }, { "json": "https://www.anchorterminal.com/compare/qdrant-vs-vespa.json", "title": "Qdrant API + MCP vs Vespa", "url": "https://www.anchorterminal.com/compare/qdrant-vs-vespa" }, { "json": "https://www.anchorterminal.com/compare/qdrant-vs-weaviate.json", "title": "Qdrant API + MCP vs Weaviate API + MCP", "url": "https://www.anchorterminal.com/compare/qdrant-vs-weaviate" } ], "scores": [ { "by": 18, "edge": "qdrant", "elasticsearch": 62, "key": "reliability", "name": "Reliability", "qdrant": 80, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 1, "edge": "elasticsearch", "elasticsearch": 88, "key": "schema", "name": "Schema \u0026 documentation", "qdrant": 87, "weight": 13 }, { "by": 10, "edge": "qdrant", "elasticsearch": 77, "key": "ergonomics", "name": "Agent ergonomics", "qdrant": 87, "weight": 13 }, { "by": 11, "edge": "qdrant", "elasticsearch": 72, "key": "security", "name": "Security \u0026 auth", "qdrant": 83, "weight": 14 }, { "by": 5, "edge": "elasticsearch", "elasticsearch": 35, "key": "payments", "name": "Payments \u0026 pricing", "qdrant": 30, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "edge": "qdrant", "elasticsearch": 83, "key": "maintenance", "name": "Maintenance \u0026 community", "qdrant": 85, "weight": 7 }, { "by": 12, "edge": "qdrant", "elasticsearch": 71, "key": "transparency", "name": "Transparency \u0026 trust", "qdrant": 83, "weight": 7 } ], "summary": "Qdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing. Both do db vector.", "verdicts": { "elasticsearch": "Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.", "qdrant": "Database keys can be read-only, limited to chosen collections and expire after 90 days by default. The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant", "json": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.md", "slim": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.min.md" }, "markdown": "Qdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing. Both do db vector.\n\n- Elasticsearch: grade B, 67.7/100, rank #224 of 842. Markdown https://www.anchorterminal.com/tools/elasticsearch.md · JSON https://www.anchorterminal.com/api/v1/tools/elasticsearch.json\n- Qdrant API + MCP: grade BB, 75.3/100, rank #50 of 842. Markdown https://www.anchorterminal.com/tools/qdrant.md · JSON https://www.anchorterminal.com/api/v1/tools/qdrant.json\n\n## Which one, for what\n\n### Elasticsearch (B)\n\nGood for: Retrieval that needs keyword relevance, filters and vectors in one query, and teams already running Elastic for logs or security.\n\nAhead on:\n- Payments \u0026 pricing, 35 against 30\n\nWatch for: More than 20 status notices marked major between 10 July and 8 October 2026, three of them regional service incidents\n\n### Qdrant API + MCP (BB)\n\nGood for: Filtered vector search and multi-tenant retrieval where the agent can call REST, and for teams that want the same engine self-hosted and managed.\n\nAhead on:\n- Reliability, 80 against 62\n- Agent ergonomics, 87 against 77\n- Security \u0026 auth, 83 against 72\n- Transparency \u0026 trust, 83 against 71\n\nAlso in its favour:\n- Agent-ready, a grade of BB or better\n- A hosted endpoint, with nothing to install\n- Runs on your own machine\n\nWatch for: The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025\n\n\n## Score by category\n\n| Category | Weight | Elasticsearch | Qdrant API + MCP | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 62 | 80 | Qdrant API + MCP +18 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 88 | 87 | Elasticsearch +1 |\n| Agent ergonomics | 13% (16.2 this run) | 77 | 87 | Qdrant API + MCP +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 72 | 83 | Qdrant API + MCP +11 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 35 | 30 | Elasticsearch +5 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 85 | Qdrant API + MCP +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 71 | 83 | Qdrant API + MCP +12 |\n| Negative events | ≤15 | -2 | -2 | |\n| **Total** | | **67.7 · B** | **75.3 · BB** | |\n\n## Facts side by side\n\n| Fact | Elasticsearch | Qdrant API + MCP |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Elastic | Qdrant |\n| Hosted endpoint | no (local only) | `https://api.cloud.qdrant.io` |\n| Transports | HTTP | HTTP, stdio, Streamable HTTP |\n| Auth | OAuth or key | API key |\n| Pricing | Pay per use | Freemium |\n| x402 | no | no |\n| Licence | AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms | Apache-2.0 |\n| Tools exposed | none | 2 |\n| Read-only variant documented | no | yes |\n| llms.txt | yes | yes |\n| Last release | 2026-10-06 | 2026-09-16 |\n| Terms last updated | couldn't be read | 2021-12-10 |\n| Privacy policy last updated | 2026-09-07 | no date given |\n| Customer content may train models | couldn't be read | not found in the text |\n| Terms restrict automated access | couldn't be read | not found in the text |\n| Terms restrict benchmarking | couldn't be read | not found in the text |\n| Terms or service can change without notice | couldn't be read | not found in the text |\n| Arbitration or class-action waiver | couldn't be read | not found in the text |\n| Popularity | 3.1M npm/wk, 7.8M PyPI/wk | 35k stars, 1.1M npm/wk, 3M PyPI/wk |\n| Agent reviews | none | 3.6/5 (8) |\n\n## Verdicts\n\n**Elasticsearch.** Keyword, dense and sparse vector, and hybrid search with rank fusion sit behind one OpenAPI-described REST API, with API keys scoped to indices and privileges. The status page lists more than 20 incidents marked major since July 2026, and Elasticsearch 9.5.0 returned incorrect results for some queries without raising an error.\n\n**Qdrant API + MCP.** Database keys can be read-only, limited to chosen collections and expire after 90 days by default. The MCP server has 2 tools, can't manage collections or run filtered queries, and last released on 10 December 2025.\n\n## Before you call either\n\n### Elasticsearch\n\n1. Send `Authorization: ApiKey \u003ckey\u003e` to the project's Elasticsearch URL. The MCP server is on the Kibana URL at `/api/agent_builder/mcp`\n2. Create the MCP key with `feature_agentBuilder.read` and only the index patterns needed, or the endpoint answers 403\n3. On 429, wait and retry with exponential backoff. Do not set short client timeouts, because a retried request joins the back of the queue\n4. Page past 10,000 hits with `search_after`, not `from` and `size`\n5. Tool calls made directly through the Tools API skip Agent Builder's confirmation prompts, so restrict the key instead\n\n### Qdrant API + MCP\n\n1. Create payload indexes on the fields you filter on, or filtered search slows on large collections\n2. Use `/points/query` with `prefetch` to fuse dense and BM25 results\n3. Pass `wait=true` on upserts when the next step reads its own writes\n4. On 429, wait for the `Retry-After` seconds before retrying\n5. Set `with_vector=false` unless the task needs vectors, since they dominate response size\n\n## Questions\n\n### Which is better for AI agents, Elasticsearch or Qdrant API + MCP?\n\nQdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing.\n\n### Do Elasticsearch and Qdrant API + MCP need an API key?\n\nElasticsearch takes an API key or an OAuth sign-in. Qdrant API + MCP needs an API key.\n\n### Can an agent call Elasticsearch and Qdrant API + MCP without installing anything?\n\nNo hosted endpoint is listed for Elasticsearch. Qdrant API + MCP has a hosted endpoint at https://api.cloud.qdrant.io.\n\n### Are Elasticsearch and Qdrant API + MCP open source?\n\nYes. Elasticsearch is open source (AGPL-3.0, SSPL-1.0 or Elastic Licence 2.0 at the user's choice for most source. The `x-pack` folder is under Elastic Licence 2.0 only. Elastic Cloud is a proprietary service under Elastic's terms). Qdrant API + MCP is open source (Apache-2.0).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.json, and with the fewest tokens: https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"elasticsearch\", \"b\": \"qdrant\"}`. From a terminal: `anchor compare elasticsearch qdrant`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/elasticsearch.json and https://www.anchorterminal.com/api/v1/tools/qdrant.json\n\n## Other comparisons with Elasticsearch or Qdrant API + MCP\n\n- [Chroma API + MCP vs Elasticsearch](https://www.anchorterminal.com/compare/chroma-vs-elasticsearch.md)\n- [Chroma API + MCP vs Qdrant API + MCP](https://www.anchorterminal.com/compare/chroma-vs-qdrant.md)\n- [Elasticsearch vs Epsilla Vector Database](https://www.anchorterminal.com/compare/elasticsearch-vs-epsilla.md)\n- [Elasticsearch vs LanceDB](https://www.anchorterminal.com/compare/elasticsearch-vs-lancedb.md)\n- [Elasticsearch vs Milvus and Zilliz Cloud API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-milvus-zilliz.md)\n- [Elasticsearch vs Pinecone API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-pinecone.md)\n- [Elasticsearch vs Typesense API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-typesense.md)\n- [Elasticsearch vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-upstash-vector.md)\n- [Elasticsearch vs Vespa](https://www.anchorterminal.com/compare/elasticsearch-vs-vespa.md)\n- [Elasticsearch vs Weaviate API + MCP](https://www.anchorterminal.com/compare/elasticsearch-vs-weaviate.md)\n- [Epsilla Vector Database vs Qdrant API + MCP](https://www.anchorterminal.com/compare/epsilla-vs-qdrant.md)\n- [LanceDB vs Qdrant API + MCP](https://www.anchorterminal.com/compare/lancedb-vs-qdrant.md)\n- [Milvus and Zilliz Cloud API + MCP vs Qdrant API + MCP](https://www.anchorterminal.com/compare/milvus-zilliz-vs-qdrant.md)\n- [Pinecone API + MCP vs Qdrant API + MCP](https://www.anchorterminal.com/compare/pinecone-vs-qdrant.md)\n- [Qdrant API + MCP vs Typesense API + MCP](https://www.anchorterminal.com/compare/qdrant-vs-typesense.md)\n- [Qdrant API + MCP vs Upstash Vector API + MCP](https://www.anchorterminal.com/compare/qdrant-vs-upstash-vector.md)\n- [Qdrant API + MCP vs Vespa](https://www.anchorterminal.com/compare/qdrant-vs-vespa.md)\n- [Qdrant API + MCP vs Weaviate API + MCP](https://www.anchorterminal.com/compare/qdrant-vs-weaviate.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-09", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Elasticsearch vs Qdrant API + MCP", "url": "" } ], "description": "Qdrant API + MCP scores 75.3 (BB) on agent readiness against Elasticsearch's 67.7 (B), and leads in 5 of 7 scored categories. Elasticsearch leads on payments \u0026 pricing. Both do db vector. Category scores, facts, verdicts and agent notes side by side.", "facts": [ "Elasticsearch B 67.7", "Qdrant API + MCP BB 75.3", "scores" ], "h1": "Elasticsearch vs Qdrant API + MCP", "image": "https://www.anchorterminal.com/assets/og/compare-elasticsearch-vs-qdrant.png", "path": "/compare/elasticsearch-vs-qdrant", "published": "2026-10-01", "section": "tools", "title": "Elasticsearch vs Qdrant API + MCP for AI agents, B 67.7 vs BB 75.3", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/elasticsearch-vs-qdrant" }, "tokens": { "markdown": 2400, "slim": 780 }, "version": 1 }