Base de Conhecimento

by mcp-dir · remote · no sign-in to list tools · v0.1.0 · published by GitHub user mcp-dir

Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes

Deletes · 1Changes · 5

Compare Registry entry

13 tools: 1 can delete or cancel things, 5 change things and 7 only read.

Scanned Oct 21, 2026

Deletes or cancels1Claude Code: deny: see these tools
Can't be undone0Claude Code: ask
Changes things5Claude Code: ask: see these tools
Only reads7Claude Code: allow: see these tools

3 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http kb https://api.mcp.ai/p_kb

Findings

Matches of fixed checks, with the text they matched.

1 warn2 info

Warnkb_remove_document
The server marks "kb_remove_document" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
Matched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "kb_remove_document" says "remove": a word for removing or ending something.
What this check looks for
Infoconnect
The description mentions "credentials".
Matched text
description: "...nticated:true and empty pending[]. When credentials are missing, returns connect_url for th..."
What this check looks for
Infomarketplace
The description mentions "credential".
Matched text
description: "...ating the tool list. If the MCP needs a credential/login, invoke returns a connect link; i..."
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

13 tools

Deletes or cancels 1Removes, cancels or revokes something.Claude Code: deny

kb_remove_documentRemove um ou mais documentos da base (apaga o original, os chunks e o índice).1 finding
Why it is in this group
- The name "kb_remove_document" says "remove": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
  The server marks "kb_remove_document" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
  Matched text
  annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "kb_remove_document" says "remove": a word for removing or ending something.
  What this check looks for
Description, as the server wrote it
Remove um ou mais documentos da base (apaga o original, os chunks e o índice). Aceita uma lista de ids.
Annotations the server declares
- title: kb_remove_document
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false

Changes things 5Creates or changes something that can be changed back.Claude Code: ask

authenticateMCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.
Annotations the server declares
- title: Authenticate
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
kb_add_textAdiciona um texto colado à base (vira um documento indexado e buscável).No findings
Why it is in this group
- The name "kb_add_text" says "add": a word for a change.
Description, as the server wrote it
Adiciona um texto colado à base (vira um documento indexado e buscável). Útil pra notas, trechos, anotações.
Annotations the server declares
- title: kb_add_text
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
kb_ingest_urlBaixa um arquivo de uma URL (.md/.txt/.docx) e o indexa na base.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it
Baixa um arquivo de uma URL (.md/.txt/.docx) e o indexa na base. Bom pra ingerir um documento remoto sem upload manual.
Annotations the server declares
- title: kb_ingest_url
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
marketplaceThe official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
  The description mentions "credential".
  Matched text
  description: "...ating the tool list. If the MCP needs a credential/login, invoke returns a connect link; i..."
  What this check looks for
Description, as the server wrote it
The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
Annotations the server declares
- title: Marketplace
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
report_bugReport a bug, missing feature, or send feedback.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
Annotations the server declares
- title: Report Bug
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

Only reads 7Looks things up and changes nothing.Claude Code: allow

connectReturns connection status and URLs.1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
Findings
- Info
  The description mentions "credentials".
  Matched text
  description: "...nticated:true and empty pending[]. When credentials are missing, returns connect_url for th..."
  What this check looks for
Description, as the server wrote it
Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
Annotations the server declares
- title: Connection Status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
kb_get_documentMetadados + status de um documento específico (sem o texto cru).Reads private dataNo findings
Why it is in this group
- The name "kb_get_document" says "get": a word for reading.
What it can reach
- private-dataThe name "kb_get_document" says "get" and "document": it reads documents.
Description, as the server wrote it
Metadados + status de um documento específico (sem o texto cru). Bulk support: accepts document_ids for batched execution.
Annotations the server declares
- title: kb_get_document
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
kb_list_accountsLista as bases de conhecimento conectadas neste install.No findings
Why it is in this group
- The name "kb_list_accounts" says "list": a word for reading.
Description, as the server wrote it
Lista as bases de conhecimento conectadas neste install. Retorna cada base com id, rótulo e um flag is_default (true quando só há uma — não precisa passar `account` nas outras tools). Com várias bases, toda kb_* aceita um `account` opcional (id ou rótulo).
Annotations the server declares
- title: kb_list_accounts
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
kb_list_documentsLista os documentos da base (id, nome, status, tamanho, nº de chunks).Reads private dataNo findings
Why it is in this group
- The name "kb_list_documents" says "list": a word for reading.
What it can reach
- private-dataThe name "kb_list_documents" says "list" and "document": it reads documents.
Description, as the server wrote it
Lista os documentos da base (id, nome, status, tamanho, nº de chunks).
Annotations the server declares
- title: kb_list_documents
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
kb_searchBusca semântica na base de conhecimento.No findings
Why it is in this group
- The name "kb_search" says "search": a word for reading.
Description, as the server wrote it
Busca semântica na base de conhecimento. Devolve os trechos (chunks) mais relevantes pra usar como contexto, com nome do arquivo de origem e score. Retrieval-only: você sintetiza a resposta a partir dos trechos.
Annotations the server declares
- title: kb_search
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
show_versionShow the current MCP platform and adapter versions.No findings
Why it is in this group
- The name "show_version" says "show": a word for reading.
Description, as the server wrote it
Show the current MCP platform and adapter versions.
Annotations the server declares
- title: Show Version
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
toolkit_infoReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Annotations the server declares
- title: Toolkit Info
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

2 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2: Reads files, mail, messages, databases, secrets, calendars or repositories.; kb_get_document
kb_list_documents
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; marketplace
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; kb_ingest_url

deny to break every path

{
  "permissions": {
    "deny": [
      "mcp__kb__kb_ingest_url"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 15:37 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 6
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://api.mcp.ai/p_kb: tools/list returned 13 tools to an anonymous client, including kb_remove_document (destructive), kb_add_text (write), kb_ingest_url (write), report_bug (write), marketplace (write) and 1 more
What this check looks for

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http kb https://api.mcp.ai/p_kb

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__kb__kb_search",
      "mcp__kb__kb_list_documents",
      "mcp__kb__kb_get_document",
      "mcp__kb__kb_list_accounts",
      "mcp__kb__show_version",
      "mcp__kb__connect",
      "mcp__kb__toolkit_info"
    ],
    "ask": [
      "mcp__kb__kb_add_text",
      "mcp__kb__kb_ingest_url",
      "mcp__kb__report_bug",
      "mcp__kb__marketplace",
      "mcp__kb__authenticate"
    ],
    "deny": [
      "mcp__kb__kb_remove_document"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as kb. Review it before you use it.

Capability tags behind 4 rules

mcp__kb__kb_list_documents private-data
mcp__kb__kb_get_document private-data
mcp__kb__kb_ingest_url outbound
mcp__kb__marketplace untrusted-input

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.mcp-dir/kb-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

6 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:39 UTC.

For agents: Markdown · JSON · report this listing