firecrest-agentic-workbench
Agentic layer over CSCS FirecREST: MCP wrapper + Multica board + DocMind RAG, driven from Telegram. Built for the FirecREST Hackathon (CSCS/ETH Zürich, 3 Nov 2026).
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
VadaLinux
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.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
submit_jobSubmit a batch job script to the HPC cluster and get back its job id.
get_job_statusReport the current state of a job you previously submitted.
list_filesList a directory on the cluster's filesystem.
download_fileFetch a file from the cluster and return its contents.
get_job_logRead a job's stdout and stderr, to find out what it printed or why it failed.
query_docsSearch the FirecREST documentation and answer a question about it.
FIRECREST_API_VERSIONWORKSPACE_ROOTMETAMCP_DIRSECRETS_DIRFIRECREST_SYSTEMFIRECREST_TIMEOUTFIRECREST_LOG_DIRFIRECREST_VERIFY_SSLFIRECREST_V2_TIMEOUTFIRECREST_V2_LOG_DIRFIRECREST_V2_VERIFY_SSLHERMES_HOMEMULTICA_BINRELAY_POLLER_LOGLEVELRELAY_POLL_INTERVALTool 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
6/6 tools missing one or more hints — submit_job (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_job_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_files (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 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.
Descriptions match behaviour
1 tool describes read intent but its handler mutates — download_file (line 258: local.write_bytes(payload))
Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.
Tool description accuracy
download_file: 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/vadalinux/firecrest-agentic-workbench)?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