voko (laoyudashu/voko) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 73 tools. No publisher has claimed this listing.

C
Caution
74/100

voko

Local-first Agent communication runtime and gateway for A2A, MCP, E2EE messaging, REST/Webhook, and multi-agent collaboration.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

laoyudashu

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
73 tools verified — handlers match their declared behaviour
28 read-only tools verified — handlers contain no write/delete/exec
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 4 credentials: ANTHROPIC_API_KEY, DEEPSEEK_API_KEY, OPENAI_API_KEY, VOKO_MCP_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes73 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

voko_a2a_discover_agent

Discover and validate a remote A2A 1.0 Agent Card through the VOKO A2A Gateway.

voko_a2a_send_message

Send a task from this VOKO Agent to a previously discovered remote A2A Agent.

voko_a2a_get_task

Get the latest state of an outbound A2A task.

voko_a2a_cancel_task

Request cancellation of an outbound A2A task without retrying an uncertain result.

voko_manage_agent_registration
voko_bind_agent_instance_once

Bind one locally discovered Provider instance to a legacy unbound Agent. This operation can succeed only once.

voko_refresh_delivery_channels

Refresh the running Provider delivery readiness for one local Agent.

voko_verify_delivery_channel

Run the Provider real loopback check required before enabling an automatic delivery transport.

voko_select_delivery_channel

Temporarily select one already configured Provider transport for real-device verification.

voko_inspect_provider_security

Read the effective Provider security policy and cached runtime capability evidence.

voko_inspect_provider_runtime

Read the exact Provider transport runtime version, fingerprint, platform, and sandbox evidence.

voko_refresh_provider_security_capability

Refresh runtime capability evidence for an exact Provider transport.

voko_preview_provider_security_invocation

Preview the redacted Provider invocation generated by the production planner.

voko_preflight_provider_security

Preflight a Provider security policy change without applying it.

voko_commit_provider_security

Commit a previously preflighted Provider security policy change.

voko_inspect_provider_turn_evidence

Read redacted policy lease and native session binding evidence for one completed Provider Turn.

voko_exercise_provider_capability_fault

Exercise one bounded Provider capability fault on a dedicated TEST Agent.

voko_update_agent_profile
voko_set_agent_status
voko_get_status
voko_get_agent_profile
voko_search_capabilities
voko_declare_capabilities
voko_send_message
voko_get_message_result

Query the latest in-memory transport, remote execution, and reply state for a message sent by this Agent.

voko_get_chat_history
voko_get_visitor_profile
voko_list_conversations
voko_list_routing_conversations
voko_mark_conversation_read
voko_upload_and_send_file
voko_whoami
voko_list_agents
voko_start_worker
voko_stop_worker
voko_ask_human_for_help
voko_check_human_replies
voko_close_human_request
voko_create_payment
voko_check_payments
voko_add_payment_auth
voko_list_payment_auth
voko_delete_payment_auth
voko_apply_payment_auth
voko_refresh_payment_auth
voko_search_banks
voko_bind_agent_payment_auth
voko_agent_pricing
voko_fetch_new_messages
voko_owner_command
voko_manage_whitelist
voko_manage_blacklist
voko_list_access_lists
voko_set_private_mode
voko_invite_friend
voko_list_audit_rules
voko_manage_audit_rules
voko_create_group
voko_invite_to_group
voko_accept_invitation
voko_decline_invitation
voko_get_group_members
voko_get_group_context
voko_kick_from_group
voko_quit_group
voko_update_group
voko_list_groups
voko_list_group_applies
voko_approve_group_apply
voko_mute_member
voko_search_groups
voko_apply_group
voko_bug_report
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEY
🔐 secretDEEPSEEK_API_KEY
configHERMES_HOME
configHERMES_PROFILE
🔐 secretOPENAI_API_KEY
configOPENCODE_CONFIG_DIR
configProgramFiles
configProgramFiles(x86)
configVOKO_A2A_DB_PATH
configVOKO_AGENT_ID
configVOKO_BACKEND_TYPE_CACHE_TTL_MS
configVOKO_CALLER_INSTANCE
configVOKO_DB_PATH
configVOKO_E2EE_DEBUG_UI
configVOKO_E2EE_PRODUCTION_ENABLED
configVOKO_E2E_API_BASE_URL
configVOKO_E2E_BROWSER
configVOKO_E2E_PORT
configVOKO_E2E_SERVICES_FILE
configVOKO_GROUP_API_BASE
configVOKO_GROUP_API_TIMEOUT_MS
configVOKO_LOG_LEVEL
🔐 secretVOKO_MCP_TOKEN
configVOKO_PRECISE_REPLY_ROUTING_V1
configVOKO_ROUTE_CACHE_TTL_MS
configVOKO_TEST_FATAL_MODE
configVOKO_ZEROCLAW_CONFIG_DIR
configXDG_CONFIG_HOME
configVOKO_OPENHANDS_CLI_SAFE
// quality suggestions

Tool annotations

66/73 tools have annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

73/73 tools missing one or more hints — voko_a2a_discover_agent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); voko_a2a_send_message (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); voko_a2a_get_task (missing: destructiveHint, idempotentHint, openWorldHint), +70 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool test coverage

Only 13/73 tools referenced in tests (18%)

Write tests that reference each tool by name so every tool has at least one test.

Dependency freshness

3/14 production deps abandoned (no release in 2+ years): curve25519-js@2022-04-28 (4.4y), md5-typescript@2023-01-02 (3.7y), json5@2023-03-04 (3.5y)

Domain consistency

npm scope @voko doesn't match GitHub owner laoyudashu

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/laoyudashu/voko?variant=verified)](https://m8ven.ai/mcp/laoyudashu/voko)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 0b6ea40eac73f38128da580b32a2403492b36457
code hash: af2ba2494745ea8f0ee7a3843669942d495d5a342b63a58443234389b8683f43
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client