CodeSherpa (boridon/code-sherpa) is an MCP server listed on the M8ven Trust Index. It scores 51 out of 100, grade D. It declares 7 tools. No publisher has claimed this listing.
Remote MCP server enabling AI clients to securely inspect repositories over SSH with read-only tools.
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
boridon
Source: Glama
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.
DENY_PATH_SEGMENTSMCP_BEARER_TOKEN(for optional legacy/manual testing)MCP_SERVER_NAME(default code-sherpa)MCP_SERVER_VERSION(default 0.1.0)REPO_ROOTSSH_HOSTSSH_KNOWN_HOSTS_PATHSSH_PRIVATE_KEY_PATHSSH_USERNAMEAll four hints declared on every tool
7/7 tools missing one or more hints — healthcheck_remote (missing: destructiveHint, idempotentHint, openWorldHint); git_status (missing: destructiveHint, idempotentHint, openWorldHint); git_diff (missing: destructiveHint, idempotentHint, openWorldHint), +4 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 annotations match behaviour
7 read-only tools perform write/delete/exec — healthcheck_remote (line 597: conn.exec(command, (err, stream) => {); git_status (line 597: conn.exec(command, (err, stream) => {); git_diff (line 597: conn.exec(command, (err, stream) => {)
Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.
Descriptions match behaviour
7 tools describe read intent but their handlers mutate — healthcheck_remote (line 597: conn.exec(command, (err, stream) => {); git_status (line 597: conn.exec(command, (err, stream) => {); git_diff (line 597: conn.exec(command, (err, stream) => {)
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool inputs are validated
5/7 tool handlers declare input schemas (71%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tests exist
No test files found
Add tests that exercise each declared tool.
Tool description accuracy
7 tools have description/behavior mismatches: healthcheck_remote: description implies read-only but handler writes/deletes/executes; git_status: description implies read-only but handler writes/deletes/executes; git_diff: 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/boridon/code-sherpa)?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