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.

C
Caution
70/100

Vibespace

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

Code Verified⚡ Live Monitored: not connected

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

Is this your MCP?

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.

// key findings
🚨
Known vulnerabilities in dependencies: 2 critical, 2 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
// tools this server exposes23 tools

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_list

List 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_read

Read one shared memory note by its slug, including its full body and the slugs of every other note that links to it (backlinks).

memory_write

Create 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_search

Search 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_delete

Permanently delete a memory note by slug. There is no undo — check memory_read first if unsure.

memory_list_by_tag

List 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_tags

List every distinct tag used across this workspace's memory notes, with how many notes carry each, most-used first.

find_backlinks

List 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_links

List 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_graph

Return 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_connections
list_tasks

List every task on this workspace's board (id, title, priority, columnId, agent, updatedAt).

get_task

Read one task by id, including its full description and taskKnowledge (long-form context separate from the instructions).

create_task

Create 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_task

Update a task's fields, including moving it through its lifecycle via columnId: todo -> in_progress -> in_review -> complete, or cancelled.

list_agents

List every stored agent profile ({name, systemPrompt, baseAgent}) in this workspace.

get_agent

Read one agent profile by id, including its full systemPrompt.

create_agent

Create a stored {name, systemPrompt} persona scoped to this workspace. systemPrompt is capped at 100000 characters; name must be unique within the workspace.

update_agent

Update an agent profile's name, systemPrompt, and/or baseAgent.

delete_agent

Delete an agent profile by id.

list_prompts

List saved, reusable prompts: every global prompt, plus this workspace's own if the workspace is registered.

list_skills
get_skill

Read one skill by name, including its full body and metadata, as returned by list_skills.

// known CVEs in dependencies2 critical2 high4 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@3.0.4GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

criticalvitest@3.0.4GHSA-9crc-q9x8-hgqq

Vitest allows Remote Code Execution when accessing a malicious website while Vitest API server is listening

highfastify@5.2.1GHSA-jx2c-rxcm-jvmq

Fastify's Content-Type header tab character allows body validation bypass

highfastify@5.2.1GHSA-mg2h-6x62-wpwc

Fastify vulnerable to invalid content-type parsing, which could lead to validation bypass

lowfastify@5.2.1GHSA-444r-cwp2-x5xf

fastify: request.protocol and request.host Spoofable via X-Forwarded-Proto/Host from Untrusted Connections

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configSHELL
configVIBEDECK_DATA_DIR
configVIBESPACE_DATA_DIR
// quality suggestions

Tool 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.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/hharsha98/vibespace?variant=verified)](https://m8ven.ai/mcp/hharsha98/vibespace)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: b9f42e7c20102047646ac7d25fd50febf6d4ff72
code hash: 1ee183f7e029534010533f20ffaeaf2e9de217f6499eacd8e8d10f5e45c50698
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

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
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client