← Back to search

@fruggr/zendesk-mcp-server

GitHub Actions Scanned 24d ago

Deep Zendesk MCP server for your AI assistant: search, draft, update and translate Help Center articles and manage Support tickets end to end — comments, triage and image attachments.

npm ↗
A
91 / 100

Versions

2.16.0latest
Jul 30, 2026
2.15.0
Jul 30, 2026
2.14.2
Jul 22, 2026
2.14.1
Jul 19, 2026
2.14.0
Jul 17, 2026
+ show 33 moreshow less
2.13.0
Jul 16, 2026
2.12.2
Jul 15, 2026
2.12.1
Jul 15, 2026
2.12.0
Jul 13, 2026
2.11.0
Jul 11, 2026
2.10.0
Jul 11, 2026
2.9.0
Jul 10, 2026
2.8.0
Jul 8, 2026
2.7.0
Jul 8, 2026
2.6.1
Jul 5, 2026
2.6.0
Jul 5, 2026
2.5.0
Jul 2, 2026
2.4.0
Jun 30, 2026
2.3.1
Jun 27, 2026
2.3.0
Jun 19, 2026
2.2.0
Jun 14, 2026
2.1.0
Jun 13, 2026
2.0.1
Jun 13, 2026
2.0.0
Jun 13, 2026
1.9.1
Jun 12, 2026
1.9.0
Jun 10, 2026
1.8.0
Jun 8, 2026
1.7.0
Jun 7, 2026
1.6.0
Jun 7, 2026
1.5.0
Jun 6, 2026
1.4.1
Jun 6, 2026
1.4.0
Jun 4, 2026
1.3.0
Jun 4, 2026
1.2.0
Jun 4, 2026
1.1.3
May 31, 2026
1.1.2
May 24, 2026
1.1.1
May 21, 2026
1.0.0
Apr 24, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 1

reload_tools
annotations: verified low

Dev only. Re-imports the Zendesk tool modules from source and re-registers them on this live session, so tool code you just edited takes effect without restarting the server or reconnecting the client. Call it once at the end of an edit cycle, before testing your changes; the refreshed tool list is announced via tools/list_changed. Only the tool modules (tickets, search, help_center, users) are reloaded — edits to shared infrastructure (HTTP client, shared definitions, server wiring) still require a full restart. Takes no arguments and makes no Zendesk API calls.

readOnlyHint false openWorldHint false idempotentHint true destructiveHint false

Permissions 3

network medium
Server uses network capabilities via: fetch(), http
shell high
Server uses shell capabilities via: child_process, execSync(), spawn()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 14

info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
info
Tool 'reload_tools' annotations are consistent annotation_checker · 80%
medium
Buffer.from base64 in fruggr-zendesk-mcp-server-fe65574/src/tools/help-center.ts:2353 entropy_analyzer · 75%
medium
Buffer.from base64 in fruggr-zendesk-mcp-server-fe65574/src/tools/tickets.ts:579 entropy_analyzer · 75%
info
package.json metadata manifest_parser · 100%
info
Tool: reload_tools manifest_parser · 85%
info
Transport: stdio manifest_parser · 90%
info
Required env vars (28) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 80%
high
Permission: shell access detected permission_analyzer · 95%
low
Permission: env_vars access detected permission_analyzer · 90%
info
SBOM generated: 39 components sbom_generator · 100%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%