MCP server Evermuse
Commit 6 de nov. de 2026Permite que agentes de IA pesquisem entrevistas de clientes, chamadas, feedbacks e roadmaps para fundamentar entregas de produto em evidências reais de clientes.
Também conhecido como Usermuse/em-plugin, em-plugin
- Stars
- 0
- Ferramentas
- 5
- Downloads, 30 dias
- —
- Versão mais recente
- 1.0.1
- Último commit
- 6 de nov. de 2026
- Licença
- MIT
O que é o MCP Evermuse?
Permite que agentes de IA pesquisem entrevistas de clientes, chamadas, feedbacks e roadmaps para fundamentar entregas de produto em evidências reais de clientes. Ele expõe 5 ferramentas, como add_source, add_signals, create_shaping_note.
Resumo gerado a partir do README do projeto
Sobre o MCP server de Evermuse
Product managers e desenvolvedores podem fundamentar suas entregas técnicas em evidências reais de clientes usando o Evermuse dentro do Claude Code ou Cursor. O servidor conecta seu agente de IA a chamadas gravadas, entrevistas e feedbacks, permitindo que ele substitua suposições genéricas por citações literais e pontos de dor específicos. Ele funciona pesquisando sua base de conhecimento existente para fornecer contexto para tarefas como escrever especificações de funcionalidades, criar planos de desenvolvimento ou realizar revisões de PR.
Para usar o servidor, você pode se autenticar via OAuth no cliente ou fornecer uma API key nas suas configurações de MCP. Uma vez conectado, você usa o comando /evermuse:setup para selecionar seu produto específico. O sistema segue um fluxo de trabalho rigoroso de fundamentação de pesquisa, execução do trabalho, citação de fontes com notas de rodapé e oferta para salvar o resultado final de volta no seu workspace do Evermuse. Isso garante que cada especificação ou roadmap permaneça vinculado às necessidades reais dos usuários por meio de ferramentas como customer_research, write_feature_spec e review_pr.
O que você pode fazer com ele
- 1Fundamentar especificações de funcionalidades em pesquisaPeça ao agente para escrever uma especificação técnica para uma nova funcionalidade usando requisitos reais de clientes.
- 2Analisar o sentimento do cliente sobre tópicos específicosConsulte o agente para descobrir o que os usuários estão dizendo sobre uma parte específica do seu produto, como onboarding ou precificação.
- 3Verificar pull requests em relação às necessidades do usuárioUse o agente para verificar se uma alteração de código está alinhada com as solicitações originais dos clientes.
Escrito a partir do README do projeto. Cada caso de uso é verificado com uma citação dele.
Como instalar o MCP Evermuse
Formatos verificados em 10 nov 2026Adicionar ao CursorAdicionar ao GooseInstalar o MCP Evermuse no Claude Code
$ claude mcp add --transport http em-plugin https://api.evermuse.com/api/mcpInstalar o MCP Evermuse no Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"em-plugin": {
"url": "https://api.evermuse.com/api/mcp"
}
}
}Instalar o MCP Evermuse no VS Code
.vscode/mcp.json
{
"servers": {
"em-plugin": {
"type": "http",
"url": "https://api.evermuse.com/api/mcp"
}
}
}Instalar o MCP Evermuse no VS Code CLI
$ code --add-mcp '{"name":"em-plugin","type":"http","url":"https://api.evermuse.com/api/mcp"}'Instalar o MCP Evermuse no Codex
$ codex mcp add em-plugin --url https://api.evermuse.com/api/mcpInstalar o MCP Evermuse no Codex config.toml
~/.codex/config.toml
[mcp_servers.em-plugin] url = "https://api.evermuse.com/api/mcp"
Instalar o MCP Evermuse no Gemini CLI
$ gemini mcp add -s user --transport http em-plugin https://api.evermuse.com/api/mcpInstalar o MCP Evermuse no Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"em-plugin": {
"url": "https://api.evermuse.com/api/mcp",
"type": "http"
}
}
}Ferramentas do MCP Evermuse 5
Detectadas a partir do READMEadd_sourceadd_signalscreate_shaping_noteupdate_signalsupdate_shaping_note
| add_source | — | |
| add_signals | — | |
| create_shaping_note | — | |
| update_signals | — | |
| update_shaping_note | — |
Verificações automatizadas
Executado em 14 de nov. de 2026Relatório completo →Ainda não verificado. Um servidor precisa de uma pontuação de 80, nenhum problema grave e dados suficientes para verificarmos. Como as verificações funcionam · O que corrigir para ganhar mais pontos
- Repositório de origem vinculado e acessívelusermuse/em-plugin is public and reachablegithub.com/usermuse/em-plugin ↗Passou
- O pacote indica este repositório como sua origemNão verificado
- Proveniência da build (atestação Sigstore)Não verificado
- Licença de código aberto (OSI)MITspdx.org/licenses/MIT.html ↗Passou
- Commit ou release no último anoLast commit or release 2026-11-06github.com/usermuse/em-plugin ↗Passou
- OpenSSF ScorecardNão verificado
- Nome do pacote não é próximo a um pacote popularNão verificado
- Nenhum aviso crítico no pacote ou em suas dependênciasNão verificado
- Sem instruções ocultas para o modelo5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPassou
- Ferramentas destrutivas estão rotuladasNo tool named like delete, drop or execPassou
- O endpoint remoto responde ao handshake do MCPHTTPS endpoint answered 401 (sign-in required)Passou
README
Ver no GitHubEvermuse for Claude Code and Cursor
Make your AI agent speak with the voice of your customers.
Evermuse is a plugin for Claude Code and Cursor that turns everyday product work — specs, dev plans, research, roadmaps, gap analyses, PR reviews — into deliverables grounded in real customer evidence. Instead of plausible-sounding generic answers, you get verbatim quotes, real needs, and actual pain points, each with a source link back to the conversation it came from. And the important things you produce get saved back into Evermuse, so your knowledge base compounds.
It combines proven PM/research methods (adapted from pm-skills) and spec-driven-development discipline (adapted from spec-kit) with the Evermuse MCP, which searches your recorded calls, interviews, and feedback.
What changes after you install it
Ask "what do customers think about our onboarding?" and instead of a guess you get:
Short answer: Onboarding friction centers on manual data entry — 7 mentions across 5 accounts, mostly frustrated.
Theme 1 — Re-keying data by hand (7 mentions / 5 accounts)
"We lose half a day every week re-keying this into the spreadsheet." — Dana K., Acme onboarding call, 12 May 2025 · View in Evermuse [^1]
Every spec gets a Customer Evidence section. Every dev plan opens with the customer quotes that justify it. Every PR review checks the diff against what customers literally asked for. That's the difference.
Install
Claude Code
# Add this repo as a plugin marketplace, then install the plugin
claude plugin marketplace add Usermuse/em-plugin
claude plugin install evermuse@evermuse
Or point at a local checkout during development:
claude plugin marketplace add /path/to/em-plugin
claude plugin install evermuse@evermuse
Cursor
Install from the Cursor Marketplace, or add just the MCP server with a one-click deeplink:
The Cursor plugin ships the skills and the MCP server.
How invocation differs between the two clients. In Claude Code, skills auto-activate — you
describe the task in plain language and the right skill fires. Cursor works differently:
skills are invoked explicitly, by typing /skill-name in chat or @skill-name to attach one
as context. So in Cursor the skill name is the command:
| Claude Code | Cursor |
|---|---|
/evermuse:spec <feature> |
/write-feature-spec |
/evermuse:research <question> |
/customer-research |
| "write a spec for bulk CSV export" (auto-activates) | /write-feature-spec (explicit) |
Because Cursor won't auto-fire a skill, the short aliases matter more there, not less — so
Cursor gets its own command layer in cursor-commands/:
/spec /dev-plan /research /setup /save
/discover /brainstorm /pricing /strategy /plan-launch …28 in total
Each carries Cursor's name / description frontmatter. The Claude versions in commands/
use a different frontmatter shape plus $ARGUMENTS, which Cursor does not support, so the two
directories are kept separate and each client reads its own.
Six Claude commands are deliberately not duplicated — business-model, gap-analysis,
release-notes, review-pr, test-scenarios and value-proposition share a name with a skill
that already does the same job, so in Cursor you invoke those as /gap-analysis etc. directly
and a duplicate command would only make the / list ambiguous.
Authenticate the MCP
The plugin bundles the Evermuse MCP server (https://api.evermuse.com/api/mcp). Before the skills can ground anything, connect it:
- Claude Code — OAuth (recommended): run
/mcpin an interactive session and authorize evermuse. - Cursor — OAuth: open Settings → MCP and authorize evermuse. Cursor registers itself dynamically (DCR), so there's no client ID to configure.
- API key (either client): add an
Authorizationheader for theevermuseserver in your MCP settings.
Then run /evermuse:setup to pick your Product and confirm grounding works. (A Product is required for every Evermuse call; a Project like Discovery/Support/Sales is optional and only needed when you're focused on one research effort.)
Quickstart
/evermuse:setup # connect + pick your product
/evermuse:research what do customers think about pricing?
/evermuse:spec bulk CSV export for the reporting page
/evermuse:dev-plan specs/bulk-csv-export/spec.md
/evermuse:review-pr 482
The doctrine (how grounding works)
Every skill follows Ground → Work → Cite → Save:
- Ground — verify the right Product, then run 2–4 differently-worded searches (declaring a nature:
evidence= customer voice,context= market,guidance= company strategy) plus verbatim quotes. - Work — apply the skill's method, shaped by what the evidence says.
- Cite — every customer-derived claim carries a source badge and a
[^n]footnote. - Save — offer to persist the deliverable back into Evermuse via
add_source.
The full doctrine lives in the using-evermuse skill, which every other skill defers to.
The MCP tools
The submitted default cloud OAuth configuration exposes these 27 tools:
| Group | Tools |
|---|---|
| Read-only: guidance | find_skills · read_skills |
| Read-only: product context | get_products · get_product_summary · get_projects |
| Read-only: workflow (start here) | customer_research · create_prd · write_brief · write_feature_spec · user_personas · user_stories · competitor_analysis · summarize_conversation |
| Read-only: evidence and sources | search · view_item · find_sources · read_source |
| Read-only: internal assets | list_competitors · get_competitor_capabilities · get_opportunities · get_shaping_notes · read_shaping_note |
| Write: additive | add_source · add_signals · create_shaping_note |
| Write: overwrites existing data (destructive) | update_signals · update_shaping_note |
Workflow tools are read-only despite their imperative names: create_prd creates nothing — you
write the document, and it is stored only if you then call a write tool.
Not every workspace gets exactly this list. Workspaces with shaping writes disabled don't get
create_shaping_note / update_shaping_note, local-storage workspaces get only the guidance
tools from the cloud endpoint, and other feature flags can add tools. tools/list is the
authority for what a given workspace is served.
A workflow tool runs the job's first grounding step and returns the methodology, so start
from one when it matches the task rather than reaching straight for search. Every
product-scoped call takes product_id as a parameter — there is no session to switch.
Tool annotations
Every tool sets all four MCP tool annotations
explicitly to true or false, plus a title.
| Tool(s) | readOnlyHint | destructiveHint | idempotentHint | openWorldHint | Why |
|---|---|---|---|---|---|
The 22 read-only tools: find_skills · read_skills · get_products · get_product_summary · get_projects · customer_research · create_prd · write_brief · write_feature_spec · user_personas · user_stories · competitor_analysis · summarize_conversation · search · view_item · find_sources · read_source · list_competitors · get_competitor_capabilities · get_opportunities · get_shaping_notes · read_shaping_note |
true |
false |
true |
false |
Retrieve guidance or authorized workspace data. They never create, overwrite, delete or publish the user's sources, signals or notes. |
add_source |
false |
false |
false |
true |
Adds a source to the caller's workspace and queues ingestion; the response confirms submission, not completion. Meeting imports can fetch a caller-supplied public HTTPS media URL (media.url), which is why it is open-world. Meeting and communication imports deduplicate on external_source + external_id, but note, document and spreadsheet modes don't, so a repeated call can create another source. It never overwrites an existing source. |
add_signals |
false |
false |
true |
false |
Adds up to 100 signals to an existing source. Replays are deduplicated on source, type and content, so repeating a call creates nothing new. |
create_shaping_note |
false |
false |
false |
false |
Creates a new shaping note and never modifies an existing one. Repeating the call creates a second note. |
update_signals |
false |
true |
false |
false |
Overwrites the passed fields on up to 100 existing signals (null clears an optional title or attribution). Signals have no version history. Repeating a title, content or type update advances the embedding revision and queues embedding work again, so a repeat has further effects. |
update_shaping_note |
false |
true |
false |
false |
Replaces each passed field outright, content and tags included. Every successful update, a repeat included, creates a new version, so it is not idempotent. Version history allows recovery, but the current fields are still overwritten. |
Idempotency here means a repeated identical call has no further effect, not that the data
can't change between calls. Every tool except add_source works only on Evermuse guidance or
the caller's own workspace data (hosted storage and embedding services included); add_source
can also download a media file from a URL the caller supplies. The third-party proxy tools
(find_tool / call_tool) are not served to OAuth clients. No tool on this surface renders UI.
Commands
Cursor — 28 plain-Markdown commands in cursor-commands/. Same short names as below, without
the evermuse: prefix (/spec, /dev-plan, /research). The six that duplicate a skill name are
omitted; invoke those as /gap-analysis, /review-pr etc. directly.
Claude Code — the /evermuse:* commands in commands/, listed here:
Flagship: /evermuse:setup · spec · dev-plan · gap-analysis · review-pr · research · release-notes · save
Discovery & execution: discover · brainstorm · triage-requests · interview · write-prd · write-stories · plan-okrs · transform-roadmap · test-scenarios · pre-mortem · red-team-prd · meeting-notes · ship-check
Strategy, research & GTM: strategy · business-model · value-proposition · market-scan · pricing · research-users · competitive-analysis · analyze-feedback · plan-launch · growth-strategy · battlecard · market-product · north-star
Skills also auto-activate when you describe the task in plain language ("write a spec for…", "what are customers saying about…", "review this PR") — you don't have to remember command names.
Skills catalog
- Foundation:
using-evermuse(the doctrine + MCP mechanics every skill uses) - Flagships:
write-feature-spec,development-plan,gap-analysis,review-pr,customer-research - Discovery:
brainstorm-ideas,deep-dive,assumptions,prioritize-features,analyze-feature-requests,opportunity-solution-tree,interview-script,summarize-conversation - Strategy:
product-strategy,product-vision,value-proposition,business-model,pricing-strategy,strategy-frameworks,strategy-red-team - Execution:
create-prd,user-stories,brainstorm-okrs,outcome-roadmap,release-notes,test-scenarios,shipping-artifacts,daily-brief - Market research:
user-personas,segmentation,customer-journey-map,market-sizing,competitor-analysis,sentiment-analysis - GTM & growth:
gtm-strategy,beachhead-segment,ideal-customer-profile,competitive-battlecard,positioning-and-messaging,north-star-metric - Onboarding & meta:
setup-evermuse,initial-report,list-capabilities,schedule-new-ingestion-tasks
skills/ is generated from the Evermuse monorepo (yarn sync:em-plugin). Do not edit it here —
open an issue instead, and the change is made upstream and synced down.
Tips
- The plugin works best when your project's
CLAUDE.mdmentions the product name — it helps the agent pick the right Evermuse Product automatically. (Optional.) - If Evermuse isn't connected, skills still run but produce ⚠ ungrounded output and tell you to authorize the MCP — they never fake evidence.
- Secondary Evermuse assets (the AI-generated roadmap, shaping notes, competitor list, research questions) are used sparingly and always labeled — customer conversations are the source of truth.
Contributing
skills/is generated. Request changes upstream in the Evermuse monorepo; a sync PR brings them here. Commands, manifests, the README and the logo are hand-written and edited here.- The setup header inlines
logomark.svg. Thesetup-evermuseskill embeds the SVG markup directly rather than loading it from a URL, so if the logomark changes, update the inline copy in that skill too. - Bump the version before merging a sync PR. Cursor re-reviews every update, so each release
needs
versionraised in.claude-plugin/plugin.json,.cursor-plugin/plugin.json,.codex-plugin/plugin.jsonand.claude-plugin/marketplace.json.
Credits
Built on phuryn/pm-skills (MIT) and github/spec-kit (MIT). See ATTRIBUTION.md. Licensed MIT — see LICENSE.
Perguntas sobre o MCP Evermuse
Como adiciono o MCP Evermuse ao Claude Code?
Execute claude mcp add --transport http em-plugin https://api.evermuse.com/api/mcp no seu terminal. Adicione --scope user para torná-lo disponível em todos os projetos.
Como adiciono o MCP Evermuse ao Cursor?
Abra ~/.cursor/mcp.json e adicione o servidor em mcpServers, usando a configuração do Cursor mostrada na seção de instalação acima.
Quais ferramentas o MCP Evermuse oferece?
Ele expõe 5 ferramentas, incluindo add_source, add_signals, create_shaping_note, update_signals, update_shaping_note.
Como faço para autenticar o Evermuse MCP?
Você pode usar OAuth (recomendado) para Claude Code ou Cursor, ou fornecer uma API key adicionando um header de Authorization nas suas configurações de MCP.
O Evermuse funciona com Claude Code e Cursor?
Sim, o Evermuse é um plugin projetado especificamente para Claude Code e Cursor, oferecendo diferentes métodos de invocação para cada um.
Posso salvar minhas entregas geradas por IA de volta no Evermuse?
Sim, o sistema permite persistir as entregas de volta na sua base de conhecimento do Evermuse usando a ferramenta add_source.