MCP100 Assessment

Editorial verdict

Recommended for governed Elastic Agent Builder workflows when Kibana access and API credentials are least-privilege and the direct Agent Builder MCP endpoint is used instead of the deprecated package path.

Reviewed September 5, 2026

Task Fit

Mapped

Specialized workflows

Trust

Reviewed

A dated editorial review is published on the MCP detail page.

Maintenance

Date unavailable

No dated repository or package update is currently stored.

Popularity

Signals unavailable

No independently comparable adoption metric is currently stored.

Best for

Connect agents to Elastic search, observability, and security data.
Teams already using Elastic that can test with non-sensitive data and least privilege.

Not ideal for

Users who need an MCP100-recommended recommendation today
Unattended production workflows before permissions and failure behavior are reviewed

Avoid if

The connected data or account cannot be safely exposed to the selected AI client
You cannot verify least-privilege access and review write-capable tool calls

Trade-offs

First-party provenance and a clear task improve confidence, but do not replace an independent permissions and usability review.
Client transport compatibility does not prove that authentication, scopes, failure handling, and every tool behave safely.

Evidence scope

Evidence

Current source snapshot

Popularity

No MCP-specific repository metric is stored

No MCP-specific package metric is stored

Stars observation date unavailable · Downloads observation date unavailable

Repository is shared with a broader product/monorepo/CLI/tooling surface; do not present its stars as MCP-specific popularity.

Hosted MCP/service has no reviewed comparable public MCP-specific package-download metric.

Maintenance

Publisher activity observed September 24, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed September 5, 2026

Sources

Official setup docs — www.elastic.co/docs/explore-analyze/ai-features/agent-builder/mcp-server ↗

Supporting evidence (2)

Official setup docs — www.elastic.co/docs/api/doc/kibana/operation/operation-post-agent-builder-mcp ↗Official setup docs — www.elastic.co/docs/deploy-manage/app-connections/oauth-clients ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Streamable HTTP

MCP100 logic checked

claude mcp add --transport http elastic "https://YOUR_KIBANA_URL/api/agent_builder/mcp"

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Reconnect Claude Code, complete the publisher OAuth or authentication flow if prompted, confirm elastic tools are listed, and perform one read-only test.

Uninstall and revoke

Remove elastic from Claude Code, clear its stored MCP OAuth credentials, and revoke the publisher authorization if it is no longer needed.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-09-05

Evidence 1 ↗Evidence 2 ↗

Capability

What it does

Connect agents to Elastic search, observability, and security data.

Search & ResearchLegal & ComplianceSoftware & Technology

Representative uses

Connect agents to Elastic search, observability, and security data.
Teams already using Elastic that can test with non-sensitive data and least privilege.

Important limits

Users who need an MCP100-recommended recommendation today
Unattended production workflows before permissions and failure behavior are reviewed

Tools5 toolsView tools

list_indices
List Elasticsearch indices available to the connected account so an agent can discover which datasets can be queried.
get_mappings
Retrieve field mappings for a specific Elasticsearch index to understand its searchable structure and field types.
search
Run an Elasticsearch Query DSL search against connected indices and return matching documents or aggregations.
esql
Execute an ES|QL query against Elasticsearch for tabular search, filtering, aggregation, and analysis.
get_shards
Inspect shard allocation and status for all or selected Elasticsearch indices when diagnosing cluster or index health.

Context Footprint

~1K estimated schema tokens

Context impact: Low

Estimated token footprint of the MCP tool schemas exposed to the agent.

Approx. estimate

Whole-profile rough estimate only. Do not synthesize per-tool token values from this heuristic.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Elastic API-key and RBAC privilege boundaries remain primary. OAuth 2.1 applies only to deployment and product paths where Elastic documents it, including the current Agent Builder and Elastic Cloud Serverless flow; do not generalize that claim to every Elastic MCP deployment.
Permissions: Exact permissions and the read/write boundary have not yet completed MCP100 independent review; consult the linked publisher sources and use the narrowest available scope.
Data handling: Publisher-accessible account or application data may be returned to the MCP client and its selected model. Retention and subprocess behavior require candidate-specific review.
Cost: No MCP100 cost conclusion is published yet. The publisher's account plan, API usage, infrastructure, or per-action charges may apply.
Risk and cautions: Use a test workspace or non-production account, least privilege, read-only controls where available, explicit approval for mutations, and credential revocation after evaluation.

Related reviewed MCPs

Other options

Exa MCP

MCP100 Recommended

Search the web, retrieve pages, find code, and run research workflows through Exa.

Choose this instead if

Choose Exa MCP instead if search the web, retrieve pages, find code, and run research workflows through Exa.

Search the web, retrieve pages, find code, and run research workflows through Exa.

Compare with Elastic MCP View Exa MCP details

meilisearch

MCP100 Recommended

Inspect and operate Meilisearch indexes and application-search workflows.

Choose this instead if

Choose meilisearch instead if application-search development and diagnosis against Meilisearch.

Inspect and operate Meilisearch indexes and application-search workflows.

Compare with Elastic MCP View meilisearch details

opensearch

MCP100 Recommended

Explore OpenSearch indexes, mappings, cluster state, and search results.

Choose this instead if

Choose opensearch instead if search and observability investigation against governed OpenSearch deployments.

Explore OpenSearch indexes, mappings, cluster state, and search results.

Compare with Elastic MCP View opensearch details

Read publisher documentation

Publisher documentation

MCP100 source-backed summary

A concise MCP100 summary built from the reviewed publisher sources. It is not a publisher README; use the original link for the latest full documentation.

View original documentation ↗

Elastic MCP

Connect agents to Elastic search, observability, and security data.

What it can help with

Connect agents to Elastic search, observability, and security data.
Teams already using Elastic that can test with non-sensitive data and least privilege.

Important limits

Users who need an MCP100-recommended recommendation today
Unattended production workflows before permissions and failure behavior are reviewed

Loading optional publisher documentation…

FAQ

What can Elastic MCP do?

Connect agents to Elastic search, observability, and security data.

Can Elastic MCP search logs, observability, and security data?

Yes, for the Elastic data and search tools exposed by the connected MCP service. The accessible indices, observability data, and security data remain limited by the connected Elastic authorization.

Does Elastic MCP work with Codex?

Yes. MCP100 reviewed an evidence-backed setup for Codex, but has not independently verified it with a live runtime test.

What data-access risks should I consider with Elastic MCP?

Use a test workspace or non-production account, least privilege, read-only controls where available, explicit approval for mutations, and credential revocation after evaluation.

Is this an official MCP?

Elastic is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗