latch
Run more agents with less babysitting. latch holds every agent to your own ratified decisions — and the paths you've ruled out.
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
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
open-latch
Source: github_repo_search
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.
LATCH_ADAPTERLATCH_MCP_LEGACYLATCH_SESSION_IDCLAUDE_CODE_SESSION_IDCODEX_THREAD_IDLATCH_MCP_DAEMON_START_TIMEOUT_SECLATCH_MCP_DAEMONIZELATCH_MCP_RUNTIME_KEYLATCH_MCP_PROTOCOL_VERSIONLATCH_MCP_PROXY_CAPABILITY_EPOCHLATCH_MCP_START_REQUEST_EPOCHLATCH_MCP_INITIAL_PROJECT_CWDLATCH_MCP_START_REASONLATCH_MCP_LAUNCHER_LOGCODEX_HOMECLAUDE_KB_ADVERSARYLATCH_MCP_FORCE_LEGACYLATCH_MCP_ALLOW_LEGACY_FALLBACKLATCH_HOMECLAUDE_KB_HOMELATCH_REORG_PYTEST_PYTHONLATCH_KB_DIRCLAUDE_KB_DIRCLAUDE_HOMECLAUDE_KB_HEAL_CAPLATCH_OUTCOME_EVENTSCLI processes can instead set the environment variable to 0.CLAUDE_BINCODEX_BINLATCH_GATE_BACKENDCLAUDE_KB_GATE_BACKENDLATCH_MODEL_BACKENDCODEX_KB_COMPACTOR_BACKENDCLAUDE_KB_COMPACTOR_BACKENDLATCH_COMPACTOR_BACKENDLATCH_TOOL_SURFACELATCH_WIRING_VERSIONCURSOR_AGENT_BINCURSOR_KB_COMPACTOR_BACKENDCURSOR_STATE_DBXDG_CONFIG_HOMECURSOR_HOMECLAUDE_COMMANDS_DIRLATCH_DOCTOR_ALLOW_OLD_PYTHONCLAUDE_DESKTOP_CONFIGLATCH_PYTHONA working python must be on PATH, or set to its absoluteCLAUDE_KB_PYTHONpath ( remains a legacy alias).CODEX_COMPACTOR_MODELLATCH_COMPACTOR_CURSOR_MODELCURSOR_COMPACTOR_MODELCLAUDE_KB_DEBUG_LOGLATCH_SEED_MAX_LLM_CALLS_CEILINGLATCH_SEED_MAX_LLM_CALLSLATCH_SEED_LLM_CONFIRM_THRESHOLDCLAUDE_KB_GIT_SNAPSHOTLATCH_TREE_SUMMARY_MODEL_TAGCLAUDE_KB_SUMMARY_MODEL_TAGCLAUDE_KB_USERLATCH_UNLATCHEDLATCH_DISABLECLAUDE_KB_DISABLELATCH_DISABLE_WRITECLAUDE_KB_DISABLE_WRITELATCH_IN_COMPACTCLAUDE_KB_IN_COMPACTCLAUDE_KB_PRIORITY_CAPTool 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
21/21 tools missing one or more hints — kb_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kb_get (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); kb_recent (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +18 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.
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.
[](https://m8ven.ai/mcp/open-latch/latch)?variant=verified to the badge URL.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