Tamperlens MCP server
com.tamperlens/mcp·v1.43.0Was this document edited, did its redactions hold, is it safe for a model to read — Tamperlens API.
0 stars108 downloads/wk
Reviews
Write oneNobody has reviewed Tamperlens yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Tamperlens tools (5)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_redactionCheck whether a PDF's redactions actually removed anything. Covering text with a
compare_documentsCompare a candidate document against the original you already hold, and answer
inspect_caseInspect several documents of ONE case together (for example three months of bank
inspect_documentInspect a document or image for fraud and tamper signals: revisions appended after
triage_documentCHEAP PRE-FLIGHT for document intake: is this file worth ingesting, and what does it
Public scan report
scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it
- Code scan7 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 18 days ago15/15
- Maintainer identitynamespace and repository owner differ; website matches verified namespace5/10
How Tamperlens compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 4,460 AI and agents servers
- Tools
- 5
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 108
- more than 65% of 1,538 AI and agents servers with a package
What its tools let an agent do: 5 read
Release history: 3 versions in the registry since 2026-08-25, latest 2026-10-13, typically one every 48 days.
Install Tamperlens in Claude Code, Cursor or VS Code
Runs npx -y tamperlens-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add mcp -- npx -y tamperlens-mcp
What the publisher says
From the Tamperlens repository's README, as published. We do not edit it. Read it on GitHub
tamperlens-mcp
MCP server for Tamperlens — ask whether a document was edited, whether its redactions held, and whether it is safe for a model to read, before it reaches your agent's context.
// Claude Desktop / Claude Code — claude_desktop_config.json or .mcp.json
{
"mcpServers": {
"tamperlens": {
"command": "npx",
"args": ["-y", "tamperlens-mcp"],
"env": { "TAMPERLENS_API_KEY": "tl_..." }
}
}
}No key is required to try it — without one you get the anonymous allowance of 10 documents an hour. A free key at tamperlens.com/account raises that to 50 a month with no card.
Tools
Accepts PDF; Word, Excel and PowerPoint (.docx, .xlsx, .pptx and the macro-enabled twins); and JPEG, PNG, WebP, HEIC/HEIF and AVIF.
A local path or a URL
inspectdocument, checkredaction and comparedocuments (as originalUrl/candidateUrl) take either a local path or an http/https url — not both. A url is fetched by this server, on your own machine, over your own network, and only the bytes are sent on to Tamperlens. That is why the option lives here and not on the REST API: a server-side fetch of a caller-supplied URL is an SSRF risk on the API host, whereas fetching from your machine reaches only what you can already reach. It is still guarded: http/https only (re-checked at every redirect), a redirect cap, a 30s timeout (TAMPERLENSFETCHTIMEOUTMS to tune), and the same 10 MB cap, enforced on the bytes received rather than a Content-Length that can lie.
It also checks the destination IP, not just the scheme: a url that points at — or redirects to, or resolves by DNS to — a loopback, link-local/metadata (169.254.169.254), private or otherwise non-routable address is refused, and the address it connects to is pinned to the one it validated, so DNS rebinding cannot slip an internal address past the check. The check re-runs at every redirect hop. If you genuinely need to fetch from an internal host, allow-list specific addresses with TAMPERLENSFETCHALLOW_IPS (comma-separated; empty by default, and the default reaches nothing internal).
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Tamperlens: common questions
- Is Tamperlens MCP server safe?
- Mostly: it is graded B (78/100). Read the Tamperlens safety report
- How do I install Tamperlens?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Tamperlens need an API key?
- Yes. The registry entry asks for
TAMPERLENS_API_KEY. - Is Tamperlens maintained?
- The last commit was 22 days ago (2026-10-13). The latest release is v1.43.0.
- What can I use instead of Tamperlens?
- Servers from other publishers that do the same job: three.ws Provenance MCP server and Clawdcursor MCP server.
- How does Tamperlens compare with other AI and agents MCP servers?
- safety score 78/100 (higher than 57% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Tamperlens
Same job from other publishers: the closest match first, then the best rated.
- three.ws ProvenanceAppend-only, signed, on-chain-verifiable agent action log — record and audit what agents did.not reviewedEstablishedB
- ClawdcursorSafe cross-OS desktop control for any AI agent - the fallback execution layer.not reviewedEstablishedC