Vedha
NPM · @VEDHAJS/MCP
Browser testing on Playwright that checks the server, not just the screen, before it reports a pass.
Available components
Last scanned (13 hours ago)
Scores higher than 30% of npm servers
Category Testing and QA
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 4.1.5, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 99 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (Apache-2.0).Pass
- Actively maintained (last published 10 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability63
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 766 tokens (~109/item across 7 items; 7 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage90
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 71% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 11 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 10 Nov 26 47
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@vedhajs/mcp@0.1.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 99 packages
| Packages resolved | 99 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
vedha_act ~250
Run a browser action (goto, click, fill, press, ...) and return its outcome, what Vedha observed, and the page. Optional `then` chains follow-up steps.
| Name | Type | Req | Description |
|---|---|---|---|
| confirms | string | – | id of an unresolved step this one confirms |
| destructive | boolean | – | irreversible; needs operator approval |
| enabling | boolean | – | only prepares a later step |
| expect | object | – | checks Vedha runs after the action |
| intent | string | yes | why |
| mutating | boolean | – | changes data; not repeated after an unknown outcome |
| op | string | yes | – |
| reconcile | object | – | GET returning an item matching `matches` iff the effect happened |
| repeat | boolean | – | repeat a mutating action of unknown outcome |
| synchronous | boolean | – | client-side effect: unmet expect is a failure |
| target | object | – | one of: role(+name), label, text, test_id, ref |
| then | array | – | steps to run next; stops at the first that fails |
| to | object | – | drag target |
| value | string | – | url, text, option, key, path, direction or tab |
No output schema declared.
No examples provided.
vedha_bundle ~45
Save a failure bundle under --out: goal, steps, verdicts, network summary and a screenshot, replayable with `vedha replay`.
| Name | Type | Req | Description |
|---|---|---|---|
| goal | string | yes | – |
No output schema declared.
No examples provided.
vedha_close ~17
Close the browser and end the session.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
vedha_observe ~64
Read the current page without acting: an accessibility outline by default, `controls` for interactive elements only, or `region`/`detail` for one subtree by ref. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| level | string | – | – |
| ref | string | – | subtree ref |
No output schema declared.
No examples provided.
vedha_probe ~53
Read server state with a GET to a same-origin JSON path (such as /api/orders) without leaving the page. Use it to confirm whether a write took effect. Read-only.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | – |
No output schema declared.
No examples provided.
vedha_promote ~64
Generate a Playwright Test spec from the verified steps so far, with its assumptions listed. Pass `file` to save it under --out.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | – | file under --out |
| goal | string | yes | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
vedha_report ~40
Overall verdict and each step's status (verified, failed, outcome_unknown, unverified, blocked) with errors and recoveries so far. Read-only.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Vedha MCP server?
Vedha runs locally as an npm package, launched with npx -y @vedhajs/mcp --allow-domain localhost. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
npm · @vedhajs/mcp
claude mcp add hmakt99-vedha -- npx -y @vedhajs/mcp --allow-domain localhost
What is the Vedha MCP server?
Vedha is an MCP server listed in the public MCP registry as io.github.HMAKT99/vedha. Browser testing on Playwright that checks the server, not just the screen, before it reports a pass. This page covers its npm package (@vedhajs/mcp).
Is the Vedha MCP server safe to use?
Vedha scores 62 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Vedha MCP server expose?
Vedha exposes 7 tools: vedha_act, vedha_observe, vedha_probe, vedha_report, vedha_promote, and 2 more. Their descriptions and schemas cost roughly 533 tokens of context every time the server is loaded.
Is the Vedha MCP server still maintained?
Vedha is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Vedha MCP server under?
Vedha declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Vedha MCP server?
VerifyMCP ran 15 checks on Vedha, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Vedha: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.