clemmy
Local-first AI operator with persistent memory, governed tools, workflows, voice, and meetings.
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
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
Natebreynolds
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
js-yaml: maxTotalMergeKeys does not limit CPU use for empty merge sources
JS-YAML: Quadratic CPU consumption in !!omap resolution (3.x and 4.x) — CVE-2026-59870 fix not backported
undici vulnerable to downstream response desynchronization via retry interceptor
undici vulnerable to CRLF Injection via blob-like body 'type' property
undici vulnerable to cookie attribute injection via unsanitized domain and unparsed setCookie fields
CLEMENTINE_HOMEStored under CLEMENTINE_HOME, which defaults to ~/.clementine-next/.CLEMMY_MCP_ERROR_CORRECTIVECLEMMY_MCP_SCOPE_FAILOPENCLEMMY_MCP_SCOPE_FAILOPEN_MAXCLEMMY_MCP_SEMANTIC_RANKCLEMMY_PROCEDURAL_OUTCOMESCLEMMY_SCOPED_MCP_TOOLSCLEMMY_SCOPE_FROM_RECALLCLEMMY_TOOL_CHOICE_DECAYMCP_ATTACH_CONNECTED_ONLYMCP_EAGER_CONNECT_BLOCKINGTOOL_CHOICE_CONTEXT_INJECTTool 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
199/199 tools missing one or more hints — mcp_reconnect (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mcp_add (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); mcp_configure (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +196 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.
Destructive tools are labelled
4 tools perform destructive updates without destructiveHint — produce_document deletes at line 145 (rmSync(htmlPath, { force: true })); working_memory deletes at line 622 (unlinkSync(WORKING_MEMORY_FILE)); space_revert_runner deletes at line 1618 (unlinkSync(path.join(histDir, latest)))
Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.
Descriptions match behaviour
2 tools describe read intent but their handlers mutate — desktop_status (line 39: spawnSync('/usr/libexec/PlistBuddy', ['-c', `Print :${key}`, plistPath], {); working_memory (line 622: unlinkSync(WORKING_MEMORY_FILE))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
176/185 tool handlers declare input schemas (95%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Shell command execution
1 call in production code run through a shell (src/index.ts:272)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Dependency freshness
2/24 production deps stale: gray-matter@2023-07-12 (3.2y), web-push@2024-01-16 (2.7y)
Tool description accuracy
desktop_status: description implies read-only but handler writes/deletes/executes; working_memory: description implies read-only but handler writes/deletes/executes
Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.
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/natebreynolds/clemmy)?variant=verified from the 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