F
Warning
39/100
11 days ago

Warning. Serious findings were identified. Review the full report before connecting. 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

Gaia-PBC

Source: github_code

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

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Reads files from sensitive locations
Touches: ~/.config/systemd/user, ~/.config/axi, ~/.config/axi/proxy-token
🔐
You'll be asked for 4 credentials: DISCORD_TOKEN, AXI_CHATGPT_PROXY_API_KEY, ANTHROPIC_API_KEY, HTTP_API_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// 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.
configAXI_PROXY_TOKEN_FILE
🔐 secretDISCORD_TOKENyour bot token from step 2>
configSCHEDULE_TIMEZONEUS/Pacific # or your IANA timezone
configDISCORD_VERBOSE
configDISCORD_DEBUG
configLOG_LEVEL
configAXI_HARNESSclaude_code
configFLOWCODER_ENABLED1 Legacy compatibility flag. Prefer AXI_HARNESS=flowcoder or AXI_HARNESS=claude_code
configAXI_FC_WRAPFor FlowCoder, controls the automatic wrapper flowchart; unset
configAXI_SOUL_WRAP_ENABLED
configSTREAMING_DISCORD1 Stream agent responses to Discord in real-time
configCHANNEL_STATUS_ENABLEDStatus emoji prefix: Channel names show agent state at a glance (configurable via )
configCHANNEL_SORT_BY_RECENCYRecency sorting: Most recently active channels float to the top (configurable via )
configCLEAN_TOOL_MESSAGES0 Clean up tool call indicator messages after completion
configCOMPACT_THRESHOLD0.80 axi/config.py
configIDLE_SLEEP_SECONDSIdle sleep: Agents auto-sleep after (default 60, configurable).
configSTREAMING_EDIT_INTERVAL
configALLOWED_USER_IDSyour Discord user ID>
configDEFAULT_CWD/path/to/axi-assistant # absolute path to this repo
configAXI_USER_DATA/path/to/user-data # where profile, schedules, etc. live
configDISCORD_GUILD_IDyour guild ID>
configDAY_BOUNDARY_HOURNo Hour (0-23) when a new "day" starts for planning (default: 0)
configENABLE_CRASH_HANDLERWhen =1, a crash-handler agent is auto-spawned after crashes to analyze the traceback and produce a fix plan (without auto-applying).
configAXI_WORKTREES_DIR
configALLOWED_CWDS
configADMIN_ALLOWED_CWDS
configAXI_EFFORT
configAXI_CHATGPT_PROXY_BASE_URLNo Override for the ChatGPT Anthropic proxy URL when using gpt- models
configANTHROPIC_BASE_URL
🔐 secretAXI_CHATGPT_PROXY_API_KEYNo Override for the key sent to the ChatGPT Anthropic proxy
🔐 secretANTHROPIC_API_KEY
configAXI_MODELAXI_HARNESS can be claude_code or flowcoder. can be a native
configHTTP_API_PORTRoutes to an existing agent session or spawns a new one. Enabled by setting in the environment.
configHTTP_API_HOST
🔐 secretHTTP_API_TOKEN
configMAX_AWAKE_AGENTS(default 7): Maximum simultaneously awake agents. Under pressure, idle agents are aggressively slept.
configAXI_ACTIVE_CATEGORY_NAME
configAXI_CATEGORY_NAME
configAXI_KILLED_CATEGORY_NAME
configAXI_COMBINE_LIVE_CATEGORIES
configAXI_COMBINED_CATEGORY_NAME
configBOT_NAMESPACE
configFC_QUIET_COMMANDS
configFC_SHOW_OUTPUT_SCHEMA
configAXI_TEST_SENTINEL
configENABLE_WIRE_LOG
configDEFAULT_EXTENSIONS
configFLOWCODER_SEARCH_PATH
configENABLE_ROLLBACKWhen =1 and a startup crash occurs:
configOTEL_ENDPOINT
configICECAST_STREAM_URL
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

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

All four hints declared on every tool

20/20 tools missing one or more hints — discord_list_guilds (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); discord_list_channels (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); discord_read_messages (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +17 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 inputs are validated

19/20 tool handlers declare input schemas (95%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 9/20 tool handlers wrap calls in try/catch (45%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

No access to sensitive paths

Reads sensitive paths: ~/.config/systemd/user, ~/.config/axi, ~/.config/axi/proxy-token

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

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 6 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/gaia-pbc-axi-assistant-pko7ga?variant=verified)](https://m8ven.ai/mcp/gaia-pbc-axi-assistant-pko7ga)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 31fe4b7f82400c42c77f5029d6e7c16027b703c5
code hash: 3f09c513f405481af2ad8e629a1ac2a06c4aa0f83a00252cf63d771ef629a818
verified: 8/8/2026, 8:02:57 AM
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