Base de Conhecimento
REMOTE · API.MCP.AI · SCANNED OCT 4
Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability68
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 1317 tokens (~101/item across 13 items; 13 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage67
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Base de Conhecimento MCP server?
Base de Conhecimento is a hosted endpoint at https://api.mcp.ai/p_kb, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.mcp.ai
claude mcp add --transport http mcp-dir-kb-mcp 'https://api.mcp.ai/p_kb'
{
"mcpServers": {
"mcp-dir-kb-mcp": {
"url": "https://api.mcp.ai/p_kb"
}
}
} {
"servers": {
"mcp-dir-kb-mcp": {
"type": "http",
"url": "https://api.mcp.ai/p_kb"
}
}
} [mcp_servers.mcp-dir-kb-mcp] url = "https://api.mcp.ai/p_kb"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"mcp-dir-kb-mcp": {
"type": "remote",
"url": "https://api.mcp.ai/p_kb",
"enabled": true
}
}
} openclaw mcp add mcp-dir-kb-mcp --url 'https://api.mcp.ai/p_kb' --transport streamable-http
mcp_servers:
mcp-dir-kb-mcp:
url: "https://api.mcp.ai/p_kb" {
"McpServers": {
"mcp-dir-kb-mcp": {
"Transport": "http",
"Url": "https://api.mcp.ai/p_kb"
}
}
} assistant mcp add mcp-dir-kb-mcp -t streamable-http -u 'https://api.mcp.ai/p_kb'
{
"mcpServers": {
"mcp-dir-kb-mcp": {
"type": "http",
"url": "https://api.mcp.ai/p_kb"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Server version: 0.9.356 → 0.9.358 functional
- 3 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Server version: 0.9.353 → 0.9.356 functional
- 2 Oct 26 +1
- Stability: 0.97 → pass security
- 1 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Server version: 0.9.351 → 0.9.353 functional
- 30 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Sept 26 +1
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 26 Sept 26 −3
- Stability: pass → 0.80 functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 6 Oct 2026 · Probed https://api.mcp.ai/p_kb
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.ai | CN=WE1,O=Google Trust Services,C=US | 28 Sept 2026 | 27 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 1bf4d405299e078a0e62ff16cded599b |
| SANs: mcp.ai, *.mcp.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.mcp.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 3799 | 8 | Verified |
| mcp.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.mcp.ai/p_kb | Verified | 200 | |
| http (plaintext) | http://api.mcp.ai/p_kb | Inconclusive | 406 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
authenticate ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| token | string | – | – |
No output schema declared.
No examples provided.
connect ~42
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
kb_add_text ~61
Adiciona um texto colado à base (vira um documento indexado e buscável). Útil pra notas, trechos, anotações.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
| text | string | yes | – |
| title | string | yes | – |
No output schema declared.
No examples provided.
kb_get_document ~58
Metadados + status de um documento específico (sem o texto cru). Bulk support: accepts document_ids for batched execution.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
| document_id | string | yes | – |
| document_ids | array | – | – |
No output schema declared.
No examples provided.
kb_ingest_url ~64
Baixa um arquivo de uma URL (.md/.txt/.docx) e o indexa na base. Bom pra ingerir um documento remoto sem upload manual.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
| filename | string | – | – |
| url | string | yes | – |
No output schema declared.
No examples provided.
kb_list_accounts ~72
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).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
kb_list_documents ~34
Lista os documentos da base (id, nome, status, tamanho, nº de chunks).
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
No output schema declared.
No examples provided.
kb_remove_document ~50
Remove um ou mais documentos da base (apaga o original, os chunks e o índice). Aceita uma lista de ids.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
| document_ids | array | yes | – |
No output schema declared.
No examples provided.
kb_search ~77
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.
| Name | Type | Req | Description |
|---|---|---|---|
| account | string | – | – |
| query | string | yes | – |
| top_k | number | – | – |
No output schema declared.
No examples provided.
marketplace ~532
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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | – |
| arguments | string | – | – |
| cancel_comment | string | – | – |
| cancel_reason | string | – | – |
| conversation | string | – | – |
| immediate | boolean | – | – |
| limit | number | – | – |
| mcp_id | string | – | – |
| message | string | – | – |
| prompt_body | string | – | – |
| prompt_category | string | – | – |
| prompt_description | string | – | – |
| prompt_slug | string | – | – |
| prompt_targets | array | – | – |
| prompt_title | string | – | – |
| prompt_tool | string | – | – |
| prompt_vars | string | – | – |
| query | string | – | – |
| report_context | string | – | – |
| request_details | string | – | – |
| request_name | string | – | – |
| tier_slug | string | – | – |
| tool_id | string | – | – |
No output schema declared.
No examples provided.
report_bug ~50
Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | – |
| conversation | string | – | – |
| message | string | yes | – |
No output schema declared.
No examples provided.
show_version ~17
Show the current MCP platform and adapter versions.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
toolkit_info ~37
Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the Base de Conhecimento MCP server?
Base de Conhecimento is an MCP server listed in the public MCP registry as io.github.mcp-dir/kb-mcp. Your private knowledge base: upload documents (.md, .txt, .docx, PDF, images), the platform indexes. This page covers its hosted endpoint (https://api.mcp.ai/p_kb).
Is the Base de Conhecimento MCP server safe to use?
Base de Conhecimento scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Base de Conhecimento MCP server expose?
Base de Conhecimento exposes 13 tools: kb_search, kb_list_documents, kb_get_document, kb_add_text, kb_ingest_url, and 8 more. Their descriptions and schemas cost roughly 1,193 tokens of context every time the server is loaded.
Does the Base de Conhecimento MCP server require authentication?
No. We connected to Base de Conhecimento without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Base de Conhecimento MCP server still maintained?
Base de Conhecimento is still listed as active in the MCP registry. We last reached this channel on 4 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.