Inspection report
voc-mcp
Vendor MCP server from Solvea. Tool list: code-checked5.
The answer
0
What can it change in your account?
None of the 7 tools on record can change data.
name based Read and write here are inferred from tool names and descriptions, not from a test.
| Area | Access | Write tools | Read tools |
|---|---|---|---|
| Orders | · Orders no tool on record | 0 | 0 |
| Ads | · Ads no tool on record | 0 | 0 |
| Listings | R Listings read only | 0 | 2 |
| Pricing | · Pricing no tool on record | 0 | 0 |
| Inventory | R Inventory read only | 0 | 1 |
| Reports | · Reports no tool on record | 0 | 0 |
| Finance | · Finance no tool on record | 0 | 0 |
Record
The facts on file.
Tools
All 7 tools we found.
Grouped by what they do to your data. The access column shows why we put a tool there.
read Reads data 7
| Tool | Description | Area | Access basis |
|---|---|---|---|
| amazon_reviews_analyze | Produce sentiment distribution, pain points, and themes from Amazon reviews. The platform absorbs the model cost. | Other | name based |
| amazon_reviews_fetch_history | Fetch historical Amazon reviews from cached inventory. Costs 5 Credits per ASIN including variants and is read-only against cached inventory. | Inventory | name based |
| amazon_reviews_fetch_realtime | Fetch the latest Amazon reviews for an ASIN. Costs 5 Credits per ASIN including variants and may create and poll a realtime crawl task for up to 10 minutes. | Other | name based |
| extract_listing_improvements | Generate improved Amazon title, bullets, and description from review pain points. Uses model calls and may fetch reviews according to source. | Listings | name based |
| product_tagging | Tag Amazon listings into a product taxonomy and optionally create a market analysis. Costs 10 Credits per listing. | Listings | name based |
| voc_full | Fetch Amazon reviews and analyze them in one call. May create a realtime crawl task when source is realtime; review-fetch Credits apply. | Other | name based |
| voc_tagging | Convert reviews, tickets, or NPS feedback into structured L1/L2/L3 tags, sentiment, and evidence. Costs 2 Credits per item and creates an asynchronous tagging task. | Other | name based |
Method
How we checked this server.
We read the tool definitions in the source code. We did not run the server against a seller account.5
Not tested with credentials. We did not connect this server to a seller or ads account. A tool marked read can still have side effects we could not see, and a vendor can add write tools at any time. Check the list again before you grant access.
Areas come from keywords in tool names, as explained on the matrix page.
Notes
Sources for this report
- 1Source repository or product pagegithub.com
- 2Documentationgithub.com
- 3License: GitHub API repo.license (search 2026-10-30)
- 4Authentication: static scan of repo (env names / code patterns)
- 5Our MCP inventory of Oct 30, 2026: tool list, access marks, stars and last commit. GitHub repository search (22 queries, unauthenticated) -> shallow clone -> static extraction (extract_tools.py) -> optional runtime tools/list (mcp_probe.py); vendor/official from public docs. access=read|write is a name/description heuristic unless access_basis says otherwise.