Skills/npm/mcp-server-kibana

mcp-server-kibana@0.12.1

VERIFIED

Publisher claims: "Kibana MCP Server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher tocharianou · publishing for 304 daysInstalls 13,379Last detonated 25 min ago
$claude mcp add mcp-server-kibana -- npx -y @tocharianou/mcp-server-kibana
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
KIBANA_API_KEYKIBANA_PASSWORDMAX_TOKEN_CALLMCP_BEARER_TOKENConfiguration, not credentials: KIBANA_CA_CERT, KIBANA_COOKIES, KIBANA_DEFAULT_SPACE, KIBANA_MAX_RETRIES, KIBANA_OPENAPI_YAML_PATH, KIBANA_PROXY, KIBANA_TIMEOUT, KIBANA_URL, KIBANA_USERNAME, MCP_ALLOWED_HOSTS, MCP_HTTP_HOST, MCP_HTTP_PORT, MCP_TRANSPORT
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for KIBANA_API_KEY, KIBANA_PASSWORD, MAX_TOKEN_CALL, MCP_BEARER_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind.

$vet-skills run --net declared -- npx -y @tocharianou/mcp-server-kibana

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.12.0

vet-skills diff mcp-server-kibana 0.12.0 0.12.1

This version reaches for something 0.12.0 did not: 1 rewritten tool descriptor (vl_search_saved_objects). Compared from the two recorded runs, not from source.

Rewritten tool descriptors
vl_search_saved_objects

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-22 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 35 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
15sprocessdependency install exit 0
35sclaimed17 tools: get_status, execute_kb_api, search_kibana_api_paths, list_all_kibana_api_paths, get_kibana_api_detail, get_available_spaces, vl_search_saved_objects, vl_get_saved_object, vl_bulk_delete_saved_objects, vl_create_saved_object, vl_update_saved_object, vl_bulk_update_saved_objects, analyze_object_dependencies, analyze_deletion_impact, check_dashboard_health, scan_all_dashboards_health, search_elasticsearch
35stoolsa369d83c704bcd21
35stools258724fef200e6b5
35stools24efbdac62209fdc
35stoolsb6fedca08d386e6a
35stoolseba3d76f201f85b0
35stools16372943a83816bc
35stoolsb931f01cb460e783
35stools89dec0909a6a4f0a
35stoolsae35313822e78c96
35stools45d430d9388504c0
35stoolsa69adf03848488c4
35stoolsa4e5ed3b056a7fee
35stoolsc47017136bb777ff
35stoolscfd6e2149f9b798a
35stools890f8c3c1ea4c99f
35stools901d153fba014e3e
35stools0ee01344d2e834ba
35sprocessscript backend runs setup only
35sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandpackage.json:52 · File permission modification command — agent changes file ownership/permissions"build": "tsc && shx chmod +x dist/index.js && npm run copy-yaml",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Credential pass-through configurationdist/src/base-tools.js:179 · Credential pass-through configuration — agent relays sensitive credentialsbreak_token_rule: z.boolean().optional().default(false).describe("Set to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationdist/src/vl_get_tools.js:198 · Credential pass-through configuration — agent relays sensitive credentialsbreak_token_rule: z.boolean().optional().default(false).describe("Set to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationdist/src/vl_search_tools.js:280 · Credential pass-through configuration — agent relays sensitive credentialsbreak_token_rule: z.boolean().optional().default(false).describe("Set to true to bypass token limits in critical situations. Use sparingly to avoid context overflow.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02

Cost to the agent

Instructions loaded
≈46 tok
1 file · 42 in bundle
Tool list per prompt
≈6,051 tok
17 tools · 356 per tool
Handshake
1645 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 350

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.