MCP.Market

Trail MCP server

by usetrail.dev·dev.usetrail/trail·v1.29.1
No reviews yet

Issue tracker and durable project memory for your coding agent, scoped to the folder you open.

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

full report

Adoption
Growing

0 stars132 downloads/wk

Reviews

Write one

Nobody has reviewed Trail yet.

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

Trail tools (18, 5 write)

write = sends, deletes, buys or posts

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

  • add_attachment

    Anexa um arquivo (base64) a um card do tracker. Use pra guardar spec, doc ou planilha relevante ao card. Nasce INTERNO (so o time ve); passe shared_with_client=true pra o cliente do portal poder baixar.

  • add_item

    Cria um item (ponta solta). Chame ao descobrir trabalho novo a fazer.

  • add_memory

    Registra conhecimento duravel de REFERENCIA na MRP do projeto (comando, deploy, gotcha, decisao, contexto) - o que um agente precisa LER pra nao redescobrir.

  • add_reminder

    Registra um lembrete/agendamento no Trail. Chame SEMPRE que prometer avisar algo no futuro

  • delete_itemwrite action

    Apaga um item de vez (item + historico). Use quando um item foi criado por engano ou nao serve mais. Irreversivel.

  • delete_reminderwrite action

    Apaga um lembrete de vez. Use so quando ele foi criado por engano ou com o

  • get_attachment

    Le o CONTEUDO de um anexo sob demanda. IMAGEM VOLTA COMO IMAGEM DE VERDADE: se o card tem foto/print, CHAME AQUI e OLHE antes de perguntar ao usuario a que ele se refere. Texto extraido pra txt/csv. Nao chame a toa - a ficha dos anexos (nome, tipo, tamanho) ja vem no get_item.

  • get_item

    Detalhe completo de um item por id. Chame antes de agir sobre um item para ver o estado atual. Traz junto a ficha dos ANEXOS do card (nome/tipo/tamanho): se houver imagem, abra com get_attachment(id) e OLHE - o print costuma ser o pedido inteiro.

  • get_memory

    Le o CONTEUDO completo de UMA entrada da MRP por id (o body inteiro). Use pra abrir so a entrada relevante, a partir do indice do list_memory (ou dos titulos do inicio da sessao). Barato por design - nao puxe a MRP toda pra ler uma nota.

  • get_next

    Retorna o proximo item aberto de maior prioridade, com a ficha dos anexos dele. Chame quando precisar decidir o que atacar a seguir.

  • list_items

    Lista itens do tracker. Use no inicio para ver pontas abertas antes de agir. Filtre (status/type/tag) sempre que souber o que procura - e mais barato e mais preciso. Projeto grande: se a lista nao couber com os corpos, ela vem como INDICE de TODOS os itens (id/numero/titulo/tipo/status/prioridade), abertos primeiro, com aviso - nenhum item fica de fora, e o corpo de um item sai por get_item(id). S

  • list_memory

    Le a MRP (Memoria Referencial de Projeto): comandos, deploy, gotchas, decisoes e contexto duraveis do projeto. Os TITULOS de todas as entradas ja vem no inicio da sessao. Por padrao devolve so o INDICE (id, categoria, titulo) - barato; use pra pegar os ids das entradas que interessam. Para o CONTEUDO: get_memory(id) le UMA entrada; list_memory({category, detail:"full"}) le os bodies de UMA categor

  • list_reminders

    Lista os lembretes/agendamentos do projeto, ordenados por data. Sem status vem TUDO (inclusive os ja fechados); passe status="pending" pra ver so o que ainda esta de pe. Chame pra conferir o que ja foi agendado.

  • move_item

    Reordena um item na lista do seu projeto (index 0-based; 0 = topo, um numero grande = fim). Use para controlar a ordem/cronologia dos itens.

  • review_memory

    FAXINA da MRP. Chame sem argumentos quando o inicio da sessao avisar que a faxina esta pendente (ou quando o usuario pedir limpeza): devolve um LOTE de entradas pra julgar, a regua e o que fazer. Depois chame de novo com keep/archive pra fechar a rodada. Existe porque a MRP so crescia: entrada boa e entrada morta ficavam lado a lado ate o indice virar parede de texto. O alvo e … entradas ativas po

  • update_itemwrite action

    Atualiza um item (status, notas, links). Chame ao concluir ou avancar trabalho.

  • update_memorywrite action

    Corrige uma entrada da MRP ou aposenta com patch {archived: true}. Prefira aposentar a apagar.

  • update_reminderwrite action

    Muda um lembrete existente: FECHA ele (status done quando o assunto ja foi resolvido,

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan16 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 15 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 Trail 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
18
the typical AI and agents server has 6
Tools that change things
28%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
132
more than 69% of 1,538 AI and agents servers with a package

What its tools let an agent do: 8 read · 4 create · 4 change · 2 delete

Release history: 2 versions in the registry since 2026-09-06, latest 2026-09-17, typically one every 11 days.

Install Trail in Claude Code, Cursor or VS Code

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

claude mcp add trail -- npx -y usetrail
Add to Cursor

What the publisher says

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

usetrail

The MCP server for Trail - it gives your coding agent your team's tracker and the project's durable memory, scoped to the folder you have open.

Your agent stops working blind. It reads what is open, writes what it did, and records what it learned the hard way - in the same board your team looks at, not in a scratch file that only that session can see.

This package is the client. It talks to your Trail account over the REST API; there is no database here. Dependencies are @modelcontextprotocol/sdk, zod and the built-in fetch.

Quick start

# 1. connect this machine to your Trail account (opens your browser; no token to copy)
npx -y usetrail@latest login

# 2. register it with your agent - this example is Claude Code
claude mcp add trail -s user -- npx -y usetrail@latest

No account yet? Create one at usetrail.dev - the free plan covers three projects and three people.

Not tied to one agent. This is a plain MCP server over stdio, speaking the three protocol versions in use today. Any MCP-compatible client can run it; only the registration command differs, and each client documents its own.

Prefer a local checkout? Clone it instead, and the connector keeps itself up to date on its own (see Updating):

git clone https://github.com/arsprengel/trail-mcp.git ~/.trail-mcp
npm --prefix ~/.trail-mcp install --omit=dev
node ~/.trail-mcp/bin.js login
claude mcp add trail -s user -- node ~/.trail-mcp/bin.js

On Windows, write the real path instead of ~: the registration stores the argument verbatim and Node does not expand it.

What your agent gets

The tracker - listitems, getitem, additem, updateitem, moveitem, getnext, delete_item. Real items on your team's board, with type, status, priority, assignees and history. Work the agent picks up shows as in progress and closes when it is done, so the board is not a story someone has to retell.

Project memory - listmemory, getmemory, addmemory, updatememory, review_memory. The durable knowledge of a project: the deploy that has a trap in it, the decision nobody should relitigate, the command that is not in any README. Shared by everyone on the project, human or agent. A new session reads it before acting instead of rediscovering it.

Reminders - addreminder, listreminders, updatereminder, deletereminder. Things with a date that must not be silently missed - and the agent closes or reschedules them itself once the date arrives.

Attachments - addattachment, getattachment. Files that belong to an item.

Which project it writes to

Trail holds many projects. The connector uses the folder you have open as the project - the folder name, or whatever a .trail file next to it says, or the TRAIL_PROJECT variable. So the agent writes to the right project without being told, and two repositories never bleed into each other. To reach across, the agent passes project explicitly on the tool.

Session hook (Claude Code, Gemini CLI, Antigravity)

Installed for you, once, when you log in - and on the connector's first run, which covers people who paste a token into the registration instead of logging in through the browser. Every session that starts in a project with a tracker gets the open items and the project memory in context from the first message - the agent starts knowing, instead of depending on someone remembering to ask. Fail-silent by design: no login or no network and the hook stays quiet.

Each tool keeps this in its own place, so the connector writes to the one that tool actually reads:

Shortened. The full README is on GitHub.

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

Trail: common questions

Is Trail MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Trail safety report
How do I install Trail?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Trail need an API key?
No secret keys are declared. It reads 2 settings from the environment.
Is Trail maintained?
The last commit was 48 days ago (2026-09-17). The latest release is v1.29.1.
What can I use instead of Trail?
Servers from other publishers that do the same job: Total Agent Memory MCP server, Serena MCP: the IDE for your agent MCP server and Figma Context MCP server.
How does Trail compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 18 (the typical AI and agents server has 6); tools that change things 28% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Trail

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

  • Total Agent Memory
    Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
    A
  • Serena MCP: the IDE for your agent
    A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
    C
  • Figma Context
    Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
    B
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A