← Back to search

@kosli/mcp-server

GitHub Actions Scanned 9d ago

Model Context Protocol server for the Kosli API

npm ↗
A
92.2 / 100

Versions

0.4.0latest
Jul 27, 2026
0.3.0
May 4, 2026
0.2.1
May 1, 2026
0.2.0
May 1, 2026
0.1.0
May 1, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 3

search_actions
annotations: mismatch low

Search for available Kosli API actions by natural-language query. Returns matching actions with their IDs, descriptions, and parameter schemas. Use this to discover what actions are available before calling execute_read_action or execute_write_action. The configured Kosli org is "${config.org}".

limit number query string
readOnlyHint true destructiveHint true
execute_read_action
annotations: mismatch low

Execute a read-only (GET) Kosli API action by its ID with the given parameters. Use search_actions first to find the action ID and required parameters. The 'org' parameter defaults to "${config.org}" — you do not need to supply it unless querying a different organization.

fields array params record actionId string
readOnlyHint true destructiveHint true
execute_write_action
annotations: verified low

Execute a write (POST, PUT, PATCH, DELETE) Kosli API action by its ID with the given parameters. Use search_actions first to find the action ID and required parameters. The 'org' parameter defaults to "${config.org}" — you do not need to supply it unless querying a different organization.

fields array params record actionId string
readOnlyHint false destructiveHint true

Permissions 2

network medium
Server uses network capabilities via: fetch()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 15

medium
Tool 'search_actions' claims destructive but name implies read-only operation annotation_checker · 80%
medium
Tool 'execute_read_action' claims readOnly but name implies write operation annotation_checker · 80%
info
Tool 'execute_write_action' annotations are consistent annotation_checker · 80%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
info
package.json metadata manifest_parser · 100%
info
Tool: search_actions manifest_parser · 85%
info
Tool: execute_read_action manifest_parser · 85%
info
Tool: execute_write_action manifest_parser · 85%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (4) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 70%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 192 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%