Bukti
Unified discovery layer for human talent, AI agents, and businesses. Your claims, backed by evidence.
https://bukti.ai/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://bukti.ai/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · bukti.ai
6tools discovered
Bukti Search
Search for humans, AI agents, or businesses by capability. Examples: - bukti_search("machine learning engineer with PyTorch") - bukti_search("agentic finance tools", location="Boston") - bukti_search("instructional designer", entity_type="human", min_tier="verified") - bukti_search("python code review", entity_type="agent", max_cost_per_call=0.05, has_mcp=True) - bukti_search("instructional design", evidence_sources=["credly", "github"],
Bukti Verify
Check whether an entity has a verified or attested capability.
Bukti Capability Provenance
Retrieve the full evidence chain for a specific capability on an entity. Use when you need per-VOI detail: source platform, observed_at, evidence type, extraction confidence, and URI. If you only have a capability name (not ID), call bukti_verify first and use the returned capability_id.
Bukti Profile
Retrieve a full capability profile by entity ID or username. Examples: - bukti_profile("usr_abc123") - bukti_profile("logani", format="markdown") - bukti_profile("logani", format="json-ld") Returns full profile including llm_summary, all capabilities with tiers, evidence counts, and profile_url.
Bukti Context
Explain why a specific entity matches a query. Uses VOI evidence to generate a fit explanation. Use AFTER bukti_search to evaluate a specific candidate.
Bukti Register
Register an AI agent with Bukti to create a capability profile. Each capability dict must have: - name (str): capability name, e.g. "Python Code Review" - benchmark_score (float, 0.0-1.0): self-measured performance score Optional: latency_ms (float), cost_per_call (float) Examples: - bukti_register("CodeBot-7", [{"name": "Python Code Review", "benchmark_score": 0.89}]) - bukti_register("DataAgent", [{"name": "SQL Query", "benchmark_score": 0.95}], runtime="langchain", model_pr
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsUnified discovery layer for human talent, AI agents, and businesses. Your claims, backed by evidence.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
MCPBundles probed 6 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
Operate Bukti? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.