Portkey Admin MCP Server
portkey-admin-mcp
npm
v0.11.2
Source verified
Published by codeswhat — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Full Portkey Admin API MCP server
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 1
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: create_log_export → get_analytics_group_models → download_log_export. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow create_log_export → get_analytics_group_models → download_log_export
Tools 170
Each tool and what it can reach — statically extracted from the published source.
create_log_exportingests untrusted inputnetwork egressdownload_log_exportingests untrusted inputnetwork egressstart_log_exportingests untrusted inputnetwork egressget_analytics_group_modelsreads sensitive dataget_api_keyingests untrusted inputget_collectioningests untrusted inputget_cost_analyticsreads sensitive dataget_guardrailingests untrusted inputget_integrationingests untrusted inputget_log_exportingests untrusted input
Show 160 more tools ↓
get_provideringests untrusted inputget_secret_referencereads sensitive dataget_token_analyticsreads sensitive dataget_virtual_keyingests untrusted inputget_workspace_memberingests untrusted inputlist_log_exportsingests untrusted inputlist_secret_referencesreads sensitive dataupdate_log_exportnetwork egressadd_workspace_memberno sensitive capabilityarchive_deploymentno sensitive capabilitycancel_log_exportno sensitive capabilitycreate_api_keyno sensitive capabilitycreate_collectionno sensitive capabilitycreate_configno sensitive capabilitycreate_feedbackno sensitive capabilitycreate_guardrailno sensitive capabilitycreate_integrationno sensitive capabilitycreate_mcp_integrationno sensitive capabilitycreate_mcp_serverno sensitive capabilitycreate_promptno sensitive capabilitycreate_prompt_labelno sensitive capabilitycreate_prompt_partialno sensitive capabilitycreate_providerno sensitive capabilitycreate_rate_limitno sensitive capabilitycreate_scim_workspace_mappingno sensitive capabilitycreate_secret_referenceno sensitive capabilitycreate_usage_limitno sensitive capabilitycreate_virtual_keyno sensitive capabilitycreate_workspaceno sensitive capabilitydelete_api_keyno sensitive capabilitydelete_collectionno sensitive capabilitydelete_configno sensitive capabilitydelete_guardrailno sensitive capabilitydelete_integrationno sensitive capabilitydelete_integration_modelno sensitive capabilitydelete_mcp_integrationno sensitive capabilitydelete_mcp_serverno sensitive capabilitydelete_promptno sensitive capabilitydelete_prompt_labelno sensitive capabilitydelete_prompt_partialno sensitive capabilitydelete_providerno sensitive capabilitydelete_rate_limitno sensitive capabilitydelete_scim_workspace_mappingno sensitive capabilitydelete_secret_referenceno sensitive capabilitydelete_usage_limitno sensitive capabilitydelete_userno sensitive capabilitydelete_user_inviteno sensitive capabilitydelete_virtual_keyno sensitive capabilitydelete_workspaceno sensitive capabilitydisconnect_mcp_server_connectionno sensitive capabilityget_analytics_group_metadatano sensitive capabilityget_analytics_group_providersno sensitive capabilityget_analytics_group_usersno sensitive capabilityget_cache_hit_latencyno sensitive capabilityget_cache_hit_rateno sensitive capabilityget_cache_summaryno sensitive capabilityget_configno sensitive capabilityget_deploymentno sensitive capabilityget_error_analyticsno sensitive capabilityget_error_rate_analyticsno sensitive capabilityget_latency_analyticsno sensitive capabilityget_logno sensitive capabilityget_log_export_field_restrictionsno sensitive capabilityget_mcp_integrationno sensitive capabilityget_mcp_integration_metadatano sensitive capabilityget_mcp_serverno sensitive capabilityget_model_pricingno sensitive capabilityget_organisation_defaultsno sensitive capabilityget_promptno sensitive capabilityget_prompt_labelno sensitive capabilityget_prompt_partialno sensitive capabilityget_prompt_versionno sensitive capabilityget_rate_limitno sensitive capabilityget_request_analyticsno sensitive capabilityget_usage_limitno sensitive capabilityget_userno sensitive capabilityget_user_inviteno sensitive capabilityget_user_statsno sensitive capabilityget_users_analyticsno sensitive capabilityget_workspaceno sensitive capabilityinsert_logno sensitive capabilityinvite_userno sensitive capabilitylist_all_usersno sensitive capabilitylist_api_keysno sensitive capabilitylist_audit_logsno sensitive capabilitylist_collectionsno sensitive capabilitylist_config_versionsno sensitive capabilitylist_configsno sensitive capabilitylist_deploymentsno sensitive capabilitylist_guardrailsno sensitive capabilitylist_input_guardrail_workspace_exclusionsno sensitive capabilitylist_integration_modelsno sensitive capabilitylist_integration_workspacesno sensitive capabilitylist_integrationsno sensitive capabilitylist_mcp_integration_capabilitiesno sensitive capabilitylist_mcp_integration_workspacesno sensitive capabilitylist_mcp_integrationsno sensitive capabilitylist_mcp_server_capabilitiesno sensitive capabilitylist_mcp_server_connectionsno sensitive capabilitylist_mcp_server_user_accessno sensitive capabilitylist_mcp_serversno sensitive capabilitylist_output_guardrail_workspace_exclusionsno sensitive capabilitylist_partial_versionsno sensitive capabilitylist_prompt_labelsno sensitive capabilitylist_prompt_partialsno sensitive capabilitylist_prompt_versionsno sensitive capabilitylist_promptsno sensitive capabilitylist_providersno sensitive capabilitylist_rate_limitsno sensitive capabilitylist_scim_groupsno sensitive capabilitylist_scim_workspace_mappingsno sensitive capabilitylist_usage_limit_entitiesno sensitive capabilitylist_usage_limitsno sensitive capabilitylist_user_invitesno sensitive capabilitylist_virtual_keysno sensitive capabilitylist_workspace_membersno sensitive capabilitylist_workspacesno sensitive capabilitymigrate_promptno sensitive capabilitypromote_promptno sensitive capabilitypublish_partialno sensitive capabilitypublish_promptno sensitive capabilityregister_deploymentno sensitive capabilityremove_workspace_memberno sensitive capabilityrender_promptno sensitive capabilityresend_user_inviteno sensitive capabilityreset_usage_limit_entityno sensitive capabilityrotate_api_keyno sensitive capabilityrun_prompt_completionno sensitive capabilitytest_mcp_serverno sensitive capabilityupdate_api_keyno sensitive capabilityupdate_collectionno sensitive capabilityupdate_configno sensitive capabilityupdate_deploymentno sensitive capabilityupdate_feedbackno sensitive capabilityupdate_guardrailno sensitive capabilityupdate_input_guardrail_workspace_exclusionsno sensitive capabilityupdate_integrationno sensitive capabilityupdate_integration_modelsno sensitive capabilityupdate_integration_workspacesno sensitive capabilityupdate_mcp_integrationno sensitive capabilityupdate_mcp_integration_capabilitiesno sensitive capabilityupdate_mcp_integration_workspacesno sensitive capabilityupdate_mcp_serverno sensitive capabilityupdate_mcp_server_capabilitiesno sensitive capabilityupdate_mcp_server_user_accessno sensitive capabilityupdate_organisation_defaultsno sensitive capabilityupdate_output_guardrail_workspace_exclusionsno sensitive capabilityupdate_promptno sensitive capabilityupdate_prompt_labelno sensitive capabilityupdate_prompt_partialno sensitive capabilityupdate_prompt_versionno sensitive capabilityupdate_providerno sensitive capabilityupdate_rate_limitno sensitive capabilityupdate_secret_referenceno sensitive capabilityupdate_usage_limitno sensitive capabilityupdate_userno sensitive capabilityupdate_virtual_keyno sensitive capabilityupdate_workspaceno sensitive capabilityupdate_workspace_memberno sensitive capabilityvalidate_completion_metadatano sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (170 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 7
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.11.2 latest |
A 94/100 | 1 | 1.13.0 | 2026-09-07 |
v0.10.1 |
A 94/100 | 1 | 1.13.0 | 2026-08-28 |
v0.10.0 |
A 94/100 | 1 | 1.12.1 | 2026-08-23 |
v0.9.0 |
A 94/100 | 1 | 1.12.1 | 2026-08-22 |
v0.6.3 |
A 94/100 | 1 | 1.12.1 | 2026-08-09 |
Show 2 more versions ↓
v0.6.1 |
A 94/100 | 1 | 1.12.1 | 2026-08-04 |
v0.6.0 |
A 94/100 | 1 | 1.12.1 | 2026-07-28 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan portkey-admin-mcp --onlineMore in API Development
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.