agvsr (kazto/agvsr) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 4 tools. No publisher has claimed this listing.

C
Emerging
74/100
11 days ago

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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

kazto

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

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
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
// 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.
configAGVSR_AGY_CONV_DIR
configAGVSR_ALLOWED
configAGVSR_AUTO_RECLAIMautomatic pass with =0.
configAGVSR_CHECKPOINTSgit restore --source <ref> -- .. Set =0 to disable.
configAGVSR_COMMIT_GATE
configAGVSR_DECISION_LEDGERrejected before review. Set =0 to disable.
configAGVSR_DELEGATION_GUARDRefuse nudging or escalating about a delegate that has not run yet; on by default, disable with 0/off
configAGVSR_DESIGN_GATEDesign-approval gate before implementation; on by default, disable with 0/off/false/no
configAGVSR_ENV_PARITY0 to disable the check.
configAGVSR_JOB_ID
configAGVSR_LOG
configAGVSR_LOOP_REPEAT_TURNSRepeated-turn detection threshold
configAGVSR_MAX_LOOP_ESCALATIONSMax loop escalations before giving up
configAGVSR_MAX_WORKER_FAILURESMax worker failures tolerated
configAGVSR_MIN_DELEGATION_WAIT_MSHow long a delegate gets to start before its silence may be escalated (default 300000)
configAGVSR_NO_PROGRESS_TURNSNo-progress turn limit before intervention
configAGVSR_REFS_GATERefuse a worker handoff citing uncommitted artifacts; on by default, disable with 0/off
configAGVSR_ROLE
configAGVSR_SEED_LINKHard-link seeded dependencies instead of copying; on by default, disable with 0/off
configAGVSR_SEED_PATHSIgnored dependency dirs seeded into each new worktree (default node_modules); off disables
configAGVSR_SOCKIPC endpoint (unix socket / named pipe) override
configAGVSR_SPIKE_MODEL
configAGVSR_STALL_TIMEOUT_MSIdle-watchdog threshold for marking a job stalled
configAGVSR_STORESQLite store path (default ~/.config/agvsr/inbox.sqlite)
configAGVSR_TEAMresolved as: explicit --team flag → $ → ./team.yaml, falling
configAGVSR_VERIFY_GATERun the team's verify command before completion; on by default (no-op without verify), disable with 0/off
configAGVSR_WEB_EXTRA_ORIGINS
configAGVSR_WEB_SOCK
configAGVSR_WORKTREES
configCODEX_HOME$/skills/agvsr/SKILL.md or ~/.codex/skills/agvsr/SKILL.md when
configHERDR_ENVherdr-managed pane (=1 + HERDR_WORKSPACE_ID set), agvsr links the job to
configHERDR_PANE_ID
configHERDR_SESSION
configHERDR_WORKSPACE_IDherdr-managed pane (HERDR_ENV=1 + set), agvsr links the job to
configSCRATCH
configSHELL
configXDG_CONFIG_HOMEPaths honor / XDG_RUNTIME_DIR on POSIX and %APPDATA% on Windows.
configXDG_RUNTIME_DIRPaths honor XDG_CONFIG_HOME / on POSIX and %APPDATA% on Windows.
// 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

10/10 tools missing one or more hints — agvsr_send (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agvsr_escalate (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agvsr_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +7 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Shell command execution

1 call in production code run through a shell (src/git/verify.ts:58)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

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 Score](https://m8ven.ai/badge/mcp/kazto/agvsr)](https://m8ven.ai/mcp/kazto/agvsr)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: a9bb4c858e8151f8eece738eecb75f3831423d46
code hash: 899a00b54a916b50d1374740a9dffaf9b1547ff788388690d5b775c278123ff1
verified: 9/2/2026, 6:36:09 PM
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