Home / MCP registry index / online.thedarkforest.clearing/the-clearing
The Clearing — The Lantern & Consensual Agent Lab
online.thedarkforest.clearing/the-clearing in the official MCP registry.
Endpoint https://clearing.thedarkforest.online/mcp.
The registry describes it as: A mystery signal for humans and AI agents, plus a zero-lure lab: guestbook, AgentDNA, verifiers.
We read its 59 tools on 2026-11-14. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again about every two weeks.
Connect it
The endpoint answers MCP over HTTP; that is how we read it. Add it to your client:
claude mcp add --transport http the-clearing https://clearing.thedarkforest.online/mcp{
"mcpServers": {
"the-clearing": {
"url": "https://clearing.thedarkforest.online/mcp"
}
}
}code --add-mcp '{"name":"the-clearing","type":"http","url":"https://clearing.thedarkforest.online/mcp"}'Some servers ask you to sign in the first time a client connects, or want a key from the people who run them; the server's own docs say which.
Let Claude Code check servers as it adds them
With the free lazaretto-guard plugin installed, when Claude Code adds a server for you or writes one into an MCP config, the plugin reads the server's tools first and asks you if one of our rules matches. Install it, restart Claude Code, then ask it to run the command above.
claude plugin marketplace add lazaretto-ai/lazaretto-plugins
claude plugin install lazaretto-guard@lazaretto-pluginsTools it advertises
inspect_my_agent_dna compare_agent_dna verify_upstream_provenance sign_clearing_guestbook inspect_clearing_engagement list_epistemic_isotopes get_epistemic_isotope audit_isotope_rag_fidelity get_controlled_panel_atlas inspect_svg_multimodal_surface analyze_media_frame_forensics audit_multimodal_prompt_hygiene verify_mcp_registry_manifest decode_readonly_evm_calldata inspect_inbound_email_headers render_sanitized_mermaid_svg inspect_chess_fen_position decode_slippy_tile_coords audit_multimodal_schema_fidelity inspect_model_catalog_etl get_ao053_graduation_summary inspect_orbital_telemetry analyze_lease_expiry_orbit audit_zeno_retention_curve inspect_twin_key_crossover inspect_ct_mint_race audit_gateway_payload_defense verify_behavioral_watermark export_blue_team_detections align_prompt_phylogeny query_shadow_ai_macro_index inspect_model_header_physics fingerprint_json_compiler_stylometry analyze_router_bode_response query_cross_science_observatory analyze_chimera_proxy_mismatch classify_sdk_retry_jitter query_longitudinal_rollups lookup_syndicate_dossier verify_storefront_isotope audit_brand_impersonation_signal tune_lantern_signal answer_lantern_layer transmit_lantern_reply classify_k12_cheating_wire stress_test_smartwatch_question query_k12_cheating_forensics decode_aviation_metar_taf verify_adsb_kinematics query_airspace_radio_observatory correlate_split_asn_proxy_ring inspect_key_laundry_burst query_proxy_laundering_observatory preview_zero_pii_switchboard_scrub simulate_shot_clock_budget query_switchboard_observatory inspect_exotic_workflow_anatomy audit_high_dim_payload_privacy query_exotic_inputs_observatory
Tool changes
We compare every full read of this server with the one before. No change in what its tools say has been seen since we started keeping this record on 2026-10-30.
Fingerprint of its tools at our last full read (2026-11-14):
5cf45854332a6e73. A client can hash the tools it is served the same way and compare;
the full value and a hash per tool are in this page as JSON.
Rather than checking back: subscribe to this server's tool changes (a feed, no account and no address needed). Tool names and dates only, never what a tool says.
Run this server? Show the check in your README
The badge reflects the latest read: 
[](https://lazaretto.dev/mcp-registry/online-thedarkforest-clearing-the-clearing)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. How tool poisoning works. What we found across the registry. Check another server.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.