Vibespace (hharsha98/Vibespace) is an MCP server listed on the M8ven Trust Index. It scores 70 out of 100, grade C. It declares 23 tools. No publisher has claimed this listing.
An open-source agentic development environment: run Claude Code, cursor-agent, Codex and shells side by side in a terminal grid, with a kanban board that dispatches them, shared agent memory, and multi-agent orchestration.
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
hharsha98
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.
memory_listList every shared memory note in this workspace (slug, title, tags, and timestamps — not the full body). Use memory_read to fetch one note's full content.
memory_readRead one shared memory note by its slug, including its full body and the slugs of every other note that links to it (backlinks).
memory_writeCreate a new memory note (omit slug, give a title) or update an existing one (give its slug). Use [[other-slug]] in the body to link another note — including one that doesn't exist yet, which is a valid way to mark a note worth writing later.
memory_searchSearch shared memory notes by a plain-text query, matched case-insensitively against title, tags, and body. Returns matching notes' slug/title/tags, not the full body — follow up with memory_read for the ones that look relevant.
memory_deletePermanently delete a memory note by slug. There is no undo — check memory_read first if unsure.
memory_list_by_tagList every note carrying EXACTLY this tag (case-insensitive exact match, not a substring search — use memory_search for that). Use memory_list_tags first if you don't already know the tag vocabulary this workspace uses.
memory_list_tagsList every distinct tag used across this workspace's memory notes, with how many notes carry each, most-used first.
find_backlinksList every note's slug that links (via [[wikilink]]) to the given slug. Works even for a slug with no note yet — a dangling link target can still have real notes pointing at it.
find_linksList every [[wikilink]] target inside one note's body (the complement to find_backlinks, which finds incoming links instead). Each target is flagged dangling if no note exists for it yet.
memory_graphReturn this workspace's whole memory graph at once: every note (plus every dangling link target) as a node, every [[wikilink]] as an edge. The same data the web app's Graph view renders.
suggest_connectionslist_tasksList every task on this workspace's board (id, title, priority, columnId, agent, updatedAt).
get_taskRead one task by id, including its full description and taskKnowledge (long-form context separate from the instructions).
create_taskCreate a new task on this workspace's board. description is short instructions (max 5000 chars); taskKnowledge is long-form reference context (max 50000 chars) — architecture decisions, file paths, API specs, links.
update_taskUpdate a task's fields, including moving it through its lifecycle via columnId: todo -> in_progress -> in_review -> complete, or cancelled.
list_agentsList every stored agent profile ({name, systemPrompt, baseAgent}) in this workspace.
get_agentRead one agent profile by id, including its full systemPrompt.
create_agentCreate a stored {name, systemPrompt} persona scoped to this workspace. systemPrompt is capped at 100000 characters; name must be unique within the workspace.
update_agentUpdate an agent profile's name, systemPrompt, and/or baseAgent.
delete_agentDelete an agent profile by id.
list_promptsList saved, reusable prompts: every global prompt, plus this workspace's own if the workspace is registered.
list_skillsget_skillRead one skill by name, including its full body and metadata, as returned by list_skills.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening
Fastify's Content-Type header tab character allows body validation bypass
Fastify vulnerable to invalid content-type parsing, which could lead to validation bypass
fastify: request.protocol and request.host Spoofable via X-Forwarded-Proto/Host from Untrusted Connections
SHELLVIBEDECK_DATA_DIRVIBESPACE_DATA_DIRTool 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
23/23 tools missing one or more hints — memory_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); memory_write (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +20 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.
Shell command execution
1 call in production code run through a shell (src/swarm/gates.ts:43)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 2 high severity in production deps — fastify@5.2.1 (high), fastify@5.2.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Domain consistency
npm scope @vibespace doesn't match GitHub owner hharsha98
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
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/hharsha98/vibespace)?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