MCP.Market

Sighttrue MCP server

online · 100% uptime
by kaitzyy-dev·io.github.kaitzyy-dev/sighttrue·v1.0.0·1 stars

Measured readings on open-source dependencies: health, end-of-life, model prices, incidents.

B79/100grade B
What users say
No reviews yet
Be the first
Safety scan
B79/100

full report

Adoption
Growing

1 stars

Reviews

Write one

Nobody has reviewed Sighttrue yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Sighttrue tools (31, 1 write)

write = sends, deletes, buys or posts
  • advisory_severityFree

    Advisories broken down by severity rather than counted, with identifiers and dates. Requires a key; see https://sighttrue.com/pricing.

  • audit_manifestFree

    Read a whole manifest and return every reading on record for it, ordered by how much a reviewer would want to know. One call instead of one per dependency. Requires a key; see https://sighttrue.com/pricing.

  • base_image_checkFree

    For a container base image: its size, when it was last rebuilt, and whether the OS underneath it is still supported. Requires a key; see https://sighttrue.com/pricing.

  • check_before_installFree

    Call this before adding a dependency. Returns only the facts a reviewer would be annoyed to discover afterwards: whether the publisher has withdrawn the package, whether it runs scripts on the installing machine, whether its repository is archived, how many advisories are on record, whether the licence is source-available, and how long since it was actually published. Each fact carries the address of the body that published it. It does not say whether to install; it says what is on record.

  • check_eolFree

    Check whether a runtime, database or framework release is still receiving security fixes, and what to move to. Covers about two dozen products read daily from endoflife.date.

  • check_packageFree

    Read the current standing of one open-source package: downloads with the window they cover, OpenSSF scorecard, advisory count, licence, whether the repository is archived, and when it was last pushed to.

  • check_providerFree

    Recorded incidents for a hosting or API provider over a window, kept after the provider’s own status page dropped them.

  • check_stackFree

    Read a whole dependency list at once and report what is archived, what carries advisories, what has a source-available licence, and what has not been pushed to in a year. Use when reviewing a package.json, requirements.txt, Cargo.toml, composer.json or Gemfile.

  • compare_repositoriesFree

    Hold two watched repositories against each other across downloads, OpenSSF scorecard, advisories, forks, stars and findings on record. Compares only; it does not pick a winner.

  • diff_sinceFree

    What changed for a set of packages since a given date, read from the daily archive. Requires a key; see https://sighttrue.com/pricing.

  • domain_riskFree

    Whether the domains a package points at — homepage, funding, documentation — still resolve to a registered owner. Requires a key; see https://sighttrue.com/pricing.

  • explain_findingFree

    Given a finding id, return what was measured, when, by whom, and the address it can be checked at. For an agent quoting a figure into a review. Requires a key; see https://sighttrue.com/pricing.

  • find_modelFree

    Find language models by price and context window, from a catalogue read daily across sixty providers. Use this before choosing a model: prices move without announcement and training data is out of date on the day it ships.

  • funding_gapFree

    Packages that ask for funding, beside how heavily they are installed and how many people write them. Requires a key; see https://sighttrue.com/pricing.

  • help_availabilityFree

    For a technology tag: questions asked against questions answered, over time. Requires a key; see https://sighttrue.com/pricing.

  • list_readingsFree

    List every reading this server can return, what each one measures, and which require a key. Call this first if unsure which tool answers a question.

  • model_price_historyFree

    Every recorded price for a model, with the date each was read. Requires a key; see https://sighttrue.com/pricing.

  • model_withdrawnFree

    Models that were in the catalogue and no longer are, with the date last seen. Requires a key; see https://sighttrue.com/pricing.

  • package_weight_historyFree

    How the published artefact size has moved over time. Returns the readings taken, not a verdict. Requires a key; see https://sighttrue.com/pricing.

  • provider_incidentsFree

    A provider’s recorded incidents, grouped by the component that failed, over the whole archive rather than the window its status page shows. Requires a key; see https://sighttrue.com/pricing.

  • provider_terms_changedFree

    When a provider last changed its terms or pricing page, from a stored fingerprint of the page. Requires a key; see https://sighttrue.com/pricing.

  • provider_transparencyFree

    How long a provider takes to acknowledge an incident: the interval between an incident starting and its first public update. Requires a key; see https://sighttrue.com/pricing.

  • registry_healthFree

    Recorded outages of the package registries themselves, kept after their status pages drop them. Requires a key; see https://sighttrue.com/pricing.

  • runtime_deadlinesFree

    Support end dates for the runtimes a dependency set requires, including any already past. Requires a key; see https://sighttrue.com/pricing.

  • search_repositoriesFree

    Find watched repositories whose name contains a string, with their current readings. Use it to discover what is covered before calling the other tools.

  • time_to_fixFree

    Days between an advisory being published and a release appearing that postdates it, per package and as a distribution. Requires a key; see https://sighttrue.com/pricing.

  • typosquat_checkFree

    Whether a name is one edit away from a more widely installed package. States that both names exist; which one was meant is the caller’s call. Requires a key; see https://sighttrue.com/pricing.

  • watch_addFree

    Add a package to the caller’s own private watchlist, so later readings are about their stack rather than the public one. The list is private to the key that created it. Requires a key; see https://sighttrue.com/pricing.

  • watch_changesFree

    Everything that has changed across the caller’s private watchlist since a given date: withdrawals, licence changes, advisories, archived repositories and runtimes going out of support. Requires a key; see https://sighttrue.com/pricing.

  • who_can_publishwrite actionFree

    How many accounts hold publish rights on a package, as the registry lists them. Answers who can put code on your machine, which is a different question from who writes it. Requires a key; see https://sighttrue.com/pricing.

  • withdrawn_but_installedFree

    Packages whose own publisher has withdrawn them and which are still being installed heavily, with the download figure and the publisher’s notice. Requires a key; see https://sighttrue.com/pricing.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 673ms20/20
  • Tool poisoning31 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Sighttrue compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
79/100
higher than 58% of 4,460 AI and agents servers
Tools
31
the typical AI and agents server has 6
Tools that change things
3%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
101 ms
faster than 86% of 2,331 AI and agents servers
GitHub stars
1
more than 50% of 2,711 AI and agents servers

What its tools let an agent do: 29 read · 1 change · 1 run or deploy

Install Sighttrue in Claude Code, Cursor or VS Code

claude mcp add --transport http sighttrue https://sighttrue.com/api/mcp
Add to Cursor

What the publisher says

From the Sighttrue repository's README, as published. We do not edit it. Read it on GitHub

Sighttrue

sighttrue.com · your stack · compare · method · feed

Check your dependencies in CI

permissions:
  pull-requests: write   # only needed for the comment

steps:
  - uses: actions/checkout@v4
  - uses: sighttrue/sighttrue@v1
    with:
      manifest: package.json
      fail-on: withdrawn,archived,relicensed

Fails the build when a dependency's own publisher has withdrawn it — npm calls it deprecated, PyPI and crates.io call it yanked, RubyGems yanked, Packagist abandoned, NuGet deprecated — or when its repository has been archived or moved to a source-available licence, and reports advisories either way. Reads package.json, requirements.txt, pyproject.toml, Cargo.toml, composer.json and Gemfile. No key, no account, no service to sign up to — it reads published measurements and talks to OSV. A network problem is never a finding: if the readings cannot be fetched the step says so and passes, because a build that breaks when somebody else's site is down is a build that gets deleted.

On a pull request it also leaves a comment with the findings as a table, and rewrites that same comment on every push rather than adding another. A red build tells a reviewer that something is wrong; it does not tell them which dependency, or what changed about it, without opening the log. Set comment: false to report only in the step summary. A pull request from a fork gets a read-only token, so the comment is skipped there and the step still passes.

Also runs against requirements.txt and Cargo.toml.

Or install the App and change nothing

The Action needs a workflow file in every repository that wants it. The GitHub App needs one install and then watches every repository it is given, with no workflow, no key and no configuration: when a pull request adds a runtime dependency that is on the watchlist, it leaves one comment with what is on record — downloads, OpenSSF scorecard, advisory count, licence, last push — and edits that same comment on every later push.

It says nothing at all when a pull request changes no manifest, adds no dependency, or adds nothing that is tracked. That is the common case and it is the point: a bot that comments to say it found nothing gets uninstalled. It never calls a package safe, unsafe or recommended, because none of those are things this project measures.

The Action fails a build; the App only reports. Both read the same published bundle, so they cannot disagree.

An SBOM you are allowed to hand over

/stack exports the readout as a CycloneDX 1.6 document, with each dependency's advisory count, scorecard, licence, publish date and bus factor attached as properties. Built in the browser from the pasted manifest, like everything else on that page — nothing is uploaded, and there is no endpoint to send a manifest to.

It states no versions. A manifest declares ^1.6.0; it does not say what was installed, and it says nothing about the transitive tree underneath. The document says both of those things in its own metadata rather than leaving a reader to notice, because an SBOM that guessed would be worse than none: a compliance artefact asserting something nobody resolved.

Suggest something to watch

The watchlist is curated and partial, and it was chosen by hand with no method beyond judgement — its weakest point. Open an issue to argue for a repository. Every change to the list is a reviewed commit, so that issue is where the review happens.

For coding agents

An MCP server over the same readings, so an agent can answer "is this dependency healthy" from a measurement taken today rather than from training data a year old.

{ "mcpServers": { "readout": { "url": "https://sighttrue.com/api/mcp" } } }

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Sighttrue: common questions

Is Sighttrue MCP server safe?
Mostly: it is graded B (79/100). Read the Sighttrue safety report
How do I install Sighttrue?
It runs remotely at sighttrue.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Sighttrue need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Sighttrue maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v1.0.0.
Is Sighttrue up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Sighttrue?
Servers from other publishers that do the same job: mcptoon MCP server and Superlog MCP server.
How does Sighttrue compare with other AI and agents MCP servers?
safety score 79/100 (higher than 58% of 4,460 AI and agents servers); tools 31 (the typical AI and agents server has 6); tools that change things 3% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Sighttrue

Same job from other publishers: the closest match first, then the best rated.

  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A
  • Superlog
    Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
    A