freebuff-bridge
MCP server that bridges agents to Freebuff Desktop sessions, enabling project and thread management, prompt sending, queue control, and wake-on-demand via REST API, SSE, and MCP 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
toyro396133
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.
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.
list_projectsList Freebuff Desktop projects known to the orchestrator, each with its current threads.
list_threadsList threads aggregated across every configured instance, with a live overlay from the orchestrator (current harnessId, model, turnState, queuePaused, status).
get_threadGet the current state of a single thread plus the last few messages. Returns {thread, lastMessages} where lastMessages is an array of message objects with {seq, role, parts}.
send_promptSend a prompt to a Freebuff session. The agent in that session will respond as if you typed it in the Freebuff Desktop UI. Returns {ok, queued}.
stop_threadCancel the running turn of a thread (interrupts mid-response). Idempotent.
resume_threadResume a paused thread (sets queuePaused=false). Does NOT reopen threads whose status=closed — for that, use the Desktop UI.
set_agentSwitch the active harness and/or model on a thread (PATCH /v1/threads/:id). Provide model, harnessId, or both; if only one is supplied, the bridge reads the current state to fill in the missing field. Returns {agent, thread}; if `agent.rejected=true` the model wasn't allowed for your tier and the pr…
wake_freebuffLaunch Freebuff Desktop if it isn't running, then wait until its orchestrator answers. Returns {ok, alreadyRunning, exePath, port, elapsedMs}. Call this first when send_prompt/enqueue_prompt fail with 'orchestrator unreachable' (DB-only mode) — the bridge's auto-wake may already have done it, but th…
list_queueList queue items for a thread (pending + running + done, sorted by position ascending). Returns {thread, items, pending}.
enqueue_promptAppend a prompt to the thread's queue. Use instead of send_prompt when you want the work to wait for the current turn to finish (or hold until resume if queuePaused=true). Returns {item, thread}; the item has state='queued' and delivery='queue'.
reorder_queue_itemChange the position of an already-queued item. Lower position runs sooner. The bridge translates the requested position into the orchestrator's 0.0.51+ 'move-after-item' semantics automatically. Will fail with 409 if the item is no longer in 'queued' state (it became 'running' or 'done').
delete_queue_itemRemove an item from a thread's queue. Use it to drop pending prompts the user no longer wants.
edit_queue_itemReplace the prompt text of an existing queued item (item must still be in 'queued' state).
send_queue_item_nowPromote a queued item to send immediately, jumping ahead of items with lower position. Useful when the user said 'actually do this one first'.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono JWT Middleware's JWT Algorithm Confusion via Unsafe Default (HS256) Allows Token Forgery and Auth Bypass
Hono Improper Authorization vulnerability
FREEBUFF_AUTOSTARTFREEBUFF_BIND_HOSTFREEBUFF_BIND_PORTFREEBUFF_BRIDGE_ADMIN_TOKENAdmin token via env var () grants access to every instance.FREEBUFF_BRIDGE_APPDATAFREEBUFF_BRIDGE_APPDIRFREEBUFF_BRIDGE_BIND_MODEFREEBUFF_BRIDGE_HOST=0.0.0.0 =strict \FREEBUFF_BRIDGE_CONFIGFREEBUFF_BRIDGE_DBFREEBUFF_BRIDGE_DEBUGFREEBUFF_BRIDGE_HOST0.0.0.0 FREEBUFF_BRIDGE_BIND_MODE=strict \FREEBUFF_BRIDGE_LOCALAPPDATAFREEBUFF_BRIDGE_PORTFREEBUFF_BRIDGE_RATELIMIT_LIMITFREEBUFF_BRIDGE_RATELIMIT_WINDOWFREEBUFF_BRIDGE_TOKENFREEBUFF_BRIDGE_URLFREEBUFF_BRIDGE_WAKE_EXEFREEBUFF_UI_HOSTFREEBUFF_UI_PORTFREEBUFF_UI_URLPROGRAMFILESPROGRAMFILES(X86)XDG_CONFIG_HOMETool 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
14/14 tools missing one or more hints — list_projects (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); list_threads (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_thread (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 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 inputs are validated
12/14 tool handlers declare input schemas (86%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
Only 0/14 tool handlers wrap calls in try/catch (0%)
Wrap each tool handler body in try/catch and return a structured error response.
License file
No license file
Add a LICENSE file (MIT, Apache-2.0, etc.).
Shell command execution
8 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 6 high severity in production deps — @modelcontextprotocol/sdk@1 (high), hono@4.6.0 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
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/toyro396133/freebuff-bridge)?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