MCP.Market

tashan MCP server

by tashan.sh·sh.tashan/tashan·v0.1.4
No reviews yet

Check any MCP server or agent skill before installing: upkeep, real adoption, and OSV advisories.

A91/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A91/100

full report

Adoption
Growing

0 stars43 downloads/wk

Reviews

Write one

Nobody has reviewed tashan yet.

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

tashan tools (3)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit_config

    Audit the agent configuration already on this machine — every MCP server and skill the user

  • check_capability

    Check one named MCP server or skill before installing it: is it maintained, deprecated,

  • find_capability

    Find an MCP server or agent skill for a task, ranked on public evidence rather than guesswork.

Public scan report

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

no findings
  • Code scan4 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 qualitylocal package, no credentials required12/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
Overall 91/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How tashan compares

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

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Tools
3
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
43
more than 35% of 1,538 AI and agents servers with a package

What its tools let an agent do: 3 read

Install tashan in Claude Code, Cursor or VS Code

Runs npx -y tashan-cli on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add tashan -- npx -y tashan-cli
Add to Cursor

What the publisher says

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

tashan

The intelligence layer for AI capabilities. Measure what actually works.

Not another directory — an instrument that scores capabilities on public evidence (not stars, not listings, not opinions). V2 tracks the whole MCP field (official registry) and ranks it by a transparent Trust score — maintenance + freshness, gated by real adoption. Roadmap: retention/churn, expertise eval, security, controlled evals, cost.

ETHOnline 2026 — what is pre-existing and what was built in the window

Entered on the Continuity track, which is the one that admits a project that already existed. This split is stated up front so nothing here has to be taken on trust: every claim below is checkable with git log or npm view.

Pre-existing (23 July – 11 September 2026, 386 commits). The instrument itself: the SQLite pipeline, the scorer (s5, frozen and published through 2026-11-01), the four-layer security audit, the static site and its generated SEO/GEO tier, the CLI and MCP server (tashan-cli on npm, first published 2026-07-31, registry entry sh.tashan/tashan), and 34 test files. None of it counts as hackathon work and none of it is presented as such.

Built in the window (12–13 September 2026). Every commit in the window is listed by git log --since='2026-09-12T12:00:00+00:00' --oneline — a count typed here would go stale by the next commit, which is the defect this project exists to point at. The substantive ones:

Shortened. The full README is on GitHub.

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

tashan: common questions

Is tashan MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the tashan safety report
How do I install tashan?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does tashan need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is tashan maintained?
The last commit was 42 days ago (2026-09-23). The latest release is v0.1.4.
What can I use instead of tashan?
Servers from other publishers that do the same job: Pm Claude Skills MCP server, Decionis MCP server and Watch Skill MCP server.
How does tashan compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 3 (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 tashan

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

  • Pm Claude Skills
    1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP.
    A
  • Decionis
    Authorize consequential AI agent actions before execution
    A
  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • mcptoon
    MCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).
    A
  • Kiln
    Spawn an object into existence: describe it, and your agent designs it, checks it, and 3D prints it.
    B