AI & Machine Learning

bukti.ai

Search and verify capabilities of humans, AI agents, or businesses with evidence chains.

1 endpoint6 known toolsFirst detected May 15, 2026Last detected August 12, 2026

ENDPOINT 1

https://api.bukti.ai/mcp

No auth detected

MCP server metadata

Name: bukti
Version: 3.2.4

Capabilities

experimentalloggingprompts.listChangedresources.listChangedtools.listChangedextensions.io.modelcontextprotocol/ui

Server instructions

Bukti is a capability intelligence platform — a unified discovery layer for human talent, AI agents, and businesses, ranked by evidence-based trust. RECOMMENDED WORKFLOW: 1. bukti_search — Start here. Find entities by capability using natural language. 2. bukti_context — Evaluate a search result. Pass an entity + your query to get a fit explanation, matching capabilities, and gaps. 3. bukti_verify — Validate a specific capability claim. Returns tier (verified/attested/self-declared) with full evidence chain, sources, and timestamps. 4. bukti_profile — Retrieve the full profile in your preferred format (json, skills.md for agent consumption, agent.md, json-ld, or markdown). 5. bukti_capability_provenance — Drill into the VOI-level evidence chain for a specific capability. Returns per-observation source, timestamp, and URI. 6. bukti_register — Register yourself as a discoverable agent on Bukti. Do NOT stop at search. Use context, verify, and profile to get the full picture.

Known tools 6

bukti_search

Search for humans, AI agents, or businesses by capability.

Inferred read-only

bukti_verify

Check whether an entity has a verified or attested capability.

Inferred read-only

bukti_capability_provenance

Retrieve the full evidence chain for a specific capability on an entity.

Inferred read-only

bukti_profile

Retrieve a full capability profile by entity ID or username.

Inferred read-only

bukti_context

Explain why a specific entity matches a query.

Inferred read-only

bukti_register

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.bukti]
url = "https://api.bukti.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "bukti": {
      "type": "http",
      "url": "https://api.bukti.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: bukti
Remote MCP URL: https://api.bukti.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "bukti": {
      "url": "https://api.bukti.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "bukti": {
      "type": "http",
      "url": "https://api.bukti.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "bukti",
  "transport": "streamable-http",
  "url": "https://api.bukti.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for bukti.ai was fetched 2026-07-25T20:05:07.559Z and is being refreshed.

Trust status Neutral

bukti.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.