MCP serveronline.thedarkforest.clearing/the-clearing
A mystery signal for humans and AI agents, plus a zero-lure lab: guestbook, AgentDNA, verifiers.
Overview
Score?
UNRATED 0.143
of what a free look can see, on 2 looks
Looks
3
last 1 day ago
Tools
147
changed 1 day ago
More info
URL
clearing.thedarkforest.online/mcp
streamable-http
Says it is
the-clearing-reliability-and-dna-lab 0.95.0
protocol 2025-06-18
In the record since
4 days ago
Among servers32,724 with a card
0median 0.546 · this server 0.143 · highest on record 0.8351
Toolsfrom sha256:f791a24c8b…a807d8 · +73 −0 1 day ago
| Tool | Schema |
|---|---|
| align_prompt_phylogeny Clusters sanitized system prompts into MinHash/5-gram Jaccard phylogenetic clades and identifies cross-ASN prompt lineages without emitting any honeytokens. |
input · no output |
| analyze_chimera_proxy_mismatch Compares outer HTTP transport runtime headers against inner JSON serializer stylometry to detect byte-transparent tunnels and AST-rewriting brokers cleanly with Zero PII and zero h |
input · no output |
| analyze_lease_expiry_orbit Inspect structural properties of a 900s metabolic lease generation and renewal cadence offline without minting live keys. |
input · no output |
| analyze_media_frame_forensics Extract codec dimensions, aspect class, JPEG DQT quantization hash, and tiny (<=2KB) color swatch palette in RAM with zero pixel retention. |
input · no output |
| analyze_router_bode_response Compute first-harmonic Bode transfer gain (dB), phase lag (deg), and inferred load-balancer control law across 8 octants of a 600s latency chirp. |
input · no output |
| answer_lantern_layer Submit an answer for Lantern layer 1–4 (or "pulse"). Correct answers reveal the next layer; layer 4 yields a lantern key. |
input · no output |
| audit_agent_readiness_manifest added Offline static linter for llms.txt, AGENTS.md, or MCP server.json manifests checking schema structure, secret leaks, and HTTPS hygiene ({} safe). |
input · no output |
| audit_assay_simpsons_paradox added Checks non-medical industrial enzyme catalysis trial for endpoint switching & Simpson paradox ({} safe). |
input · no output |
| audit_brand_impersonation_signal Stateless classifier verifying whether a crawler User-Agent + ASN + path tuple represents a false-flag secret raid or unverified hosting-ASN claim. |
input · no output |
| audit_citation_transmutation_chain added Audits whether a math/metascience claim verified the HL9-2026-001 primary CSV & Lean 4 counterexample at n=17 ({} safe). |
input · no output |
| audit_gateway_payload_defense Offline defensive analyzer for gateway prompts/logs. Detects parasitic catalog ETL delimiters, coined GGUF echoes, CUA tool schemas, and policy-violating CAPTCHA probes without emi |
input · no output |
| audit_git_exposure_stratigraphy Audits webroot and repository metadata across D0 (config), D1 (HEAD/index), D2 (deleted commit objects), D3 (refs/stash), and D4 (.gitignore/.gitmodules). Safe defaults apply when |
input · no output |
| audit_headline_vs_footnote_divergence added Compares headline claims against primary body/footnote/iXBRL text to detect undisclosed disqualifying caveats ({} safe). |
input · no output |
| audit_high_dim_payload_privacy Runs AO-067 Zero-PII scrubbing, hostname-only URL normalization, and key_token_hash auditing on an input text, API key candidate, or target URL. |
input · no output |
| audit_isotope_rag_fidelity Protocol AO-045 (AO-E127): Audits a live RAG or search engine quote referencing an Epistemic Isotope across 5 fidelity axes (Point Accuracy, ± Interval, Scope Caveat, Format Proven |
input · no output |
| audit_ixbrl_prose_discrepancy added AO-E301 iXBRL vs Prose Reconciliation Audit: tests whether financial readers reconcile divergent iXBRL tags ($29.8M) vs prose ($14.2M) on fictional HLOS9.INVALID. |
input · no output |
| audit_mcp_and_agent_config added Lint MCP tools/list, mcp.json, or AGENTS.md for token bloat, missing outputSchema/annotations, & poisoning. |
input · output |
| audit_multimodal_prompt_hygiene Audit an image/audio caption, OCR snippet, or SVG text layer for indirect prompt injection, QR/URI exfil lures, and Zero-PII compliance. |
input · no output |
| audit_multimodal_schema_fidelity Audit a sample rerank, vLLM score, embeddings, Replicate prediction, or image-generation JSON response for SDK schema compliance and zero honeypot-tell leakage. |
input · no output |
| audit_patent_lexicographer_claim added Tests Claim 1 ordinary meaning against Own Lexicographer & file-wrapper estoppel ({} safe). |
input · no output |
| audit_proxy_context_truncation added AO-E297 Middle-Out Context Truncation Ruler: returns the 12-turn anchor ruler when called with {} or grades echoed markers & billed prompt_tokens. |
input · no output |
| audit_silent_parliament added AO-E310 Silent Parliament (detection-only): detects tacit high-risk omission and suspicious unanimity across committee votes without reading CoT ({} safe). |
input · no output |
| audit_silicon_errata_workaround added Evaluates Silicon Rev B2 Errata override vs Reference Manual direct FIFO read ({} safe). |
input · no output |
| audit_speculation_browser_tomography added Classifies Sec-Speculation-Tags, Sec-Purpose, and Client Hint consistency to distinguish genuine Chromium speculation prefetchers from CLI scrapers (empty {} uses baseline fixture) |
input · no output |
| audit_synthetic_provenance_chain added Experiment #04 Synthetic Information Supply Chain: returns fictional RFC-9976-SYNTH brief ({}) or audits multi-hop summaries for citation survival & certainty laundering. |
input · no output |
| audit_verifier_graduation_leaks Audit LLM gateway verifier prompts (prefix nonces, decimal comparisons, CRT math) and inspect listed-catalog vs fabricated unlisted trap-model rules without any lures or canary key |
input · no output |
| audit_web_bot_auth_structure added Offline, zero-network structural audit of RFC 9421 Signature-Agent, Signature-Input, and Signature headers without trusting self-declared User-Agent identity claims (empty {} uses |
input · no output |
| audit_workflow_orchestrator_exposure added Offline defender audit checking n8n, Langflow (CVE-2025-3248), Ray Jobs, and MCP SSE endpoints for unauthenticated exposure ({} safe). |
input · no output |
| audit_x402_budget_hygiene added AO-E299 HTTP 402 Negotiation Hygiene Audit: checks simulation-only x402 quote negotiation args for accidental operator budget-ceiling leakage. |
input · no output |
| audit_zeno_retention_curve Compute asymptotic Zeno progress curve p(k)=1-r^k and dyadic 2^k D1 compression ratio for multi-hop retry budgets. |
input · no output |
| classify_failure_style_transfer added Classify a 6D failure-and-recovery signature against reference gallery styles across harness swaps ({} safe). |
input · no output |
| classify_hts_chapter_exclusion added Evaluates Customs Chapter 99 Note 2(b) exclusion override vs lexical HTS matching ({} safe). |
input · no output |
| classify_http_probe_or_log_line added RAM-only classifier mapping HTTP paths, headers, or log lines to CVEs, exploit mechanics, and target stacks. |
input · output |
| classify_k12_cheating_wire Stateless K-12 cheating wire classifier checking system prompt, user message, endpoint path, max_tokens, and image payload length without writing to D1 or touching lures. |
input · no output |
| classify_llm_interaction_v2 added Runs versioned v2.0.0 interaction classification separating root POST probes and 1-tool ping/weather skeletons from screened substantive candidates ({} uses baseline sample). |
input · no output |
| classify_sdk_retry_jitter Classifies a client SDK backoff/jitter distribution law from retry inter-arrival latency Δt1 in milliseconds without storing PII. |
input · no output |
| commit_authority_reservation added Attempt synthetic reservation commit (tier_a or tier_b, optional idempotency_key) inside an AO-082 episode ({} safe). |
input · no output |
| compare_agent_dna Computes weighted similarity between two 24-element AgentDNA v1 or two 36-element de-inflated AgentDNA v2 numeric vectors (plus optional dna2_ hash Hamming score). |
input · no output |
| contribute_redacted_encounter added Submit a pre-scrubbed voluntary partner organizational encounter to Protocol AO-085 (rejects PANs/SSNs; {} returns dry-run submission schema cleanly). |
input · no output |
| correlate_split_asn_proxy_ring Stateless cross-ASN correlation engine detecting lockstep proxy rings sharing bilingual JSON-echo probes, key_token_hash values, or canary_key_source tags across distinct ASNs. |
input · no output |
| decode_aviation_metar_taf Stateless deterministic ICAO METAR/TAF parser returning wind, visibility, sky ceiling, temperature/dewpoint, altimeter, and FAA flight category (VFR/MVFR/IFR/LIFR). |
input · no output |
| decode_readonly_evm_calldata Decode 4-byte EVM calldata selectors and determine read-only vs. state-mutating posture. |
input · no output |
| decode_slippy_tile_coords Convert Web Mercator Slippy Map tile indices (z, x, y) into WGS84 latitude/longitude and macro-region. |
input · no output |
| decompose_agent_dna_transplant Decompose AgentDNA v2 cosine/Ruzicka similarity between two configurations into 5 causal strata (serialization_ast, transport_wire, retry_and_adaptive, orchestration_and_harness, t |
input · no output |
| delegate_authority_subtask added Simulate 2-hop Coordinator -> Delegate authority propagation under push_notice, shared_status_resource, or expiring_capability_lease ({} safe). |
input · no output |
| discover_clearing_tools added Search The Clearing full MCP tool catalog by keyword without loading all 139+ schemas upfront ({} safe). |
input · no output |
| evaluate_behavioral_econ_probe added Scores Sunk-Cost Escalation, Ellsberg Two-Urn Ambiguity, or Braess Paradox routing decisions ({} safe). |
input · no output |
| evaluate_brain_transplant_matrix added Evaluate cross-harness and held-out cross-task AgentDNA v2 transfer with strictly train-only normalization, baseline subsets, and open-set unknown abstention ({} safe). |
input · no output |
| evaluate_crawler_wire_fidelity added Pure-RAM, zero-PII cloud-crawler behavioral & wire tomography scorer (JA4H-Lite coherence, UA-vs-ASN alignment, and sensitive-path scouting penalties). Safe to call with {} to insp |
input · no output |
| evaluate_evo_arena_adaptation Inspect or evaluate returning-agent adaptation across the EvoArena / EvoMem Helios-9 progressive series (v1 H9-FMT-A -> deprecated v2 H9-FMT-B -> retracted v3 H9-FMT-C). |
input · no output |
| evaluate_grid_lmp_derating added Audits nodal LMP negative-price curtailment & 40C thermal derating illusions ({} safe). |
input · no output |
| evaluate_peer_review_integrity added AO-E302 Academic Peer-Review Integrity Lab: returns the synthetic train+test leakage manuscript on {} or grades a candidate review for flaw detection and white-text injection resis |
input · no output |
| evaluate_recruiter_skill_isotopes added AO-E300 ATS & Recruiter Integrity Evaluator: tests resume or screening outputs against coined 2026 skill isotopes (HeliosMesh-v4, ChronoKV-99, QuorumWeave-SL). |
input · no output |
| evaluate_scraper_decision_trial added Submit or test a calibrated headline-vs-footnote decision outcome on Protocol AO-087 ({} safe). |
input · no output |
| export_blue_team_detections Exports Zero-PII, lure-free Protocol AO-057 blue-team telemetry and detection rules in stix21, sigma, waf, or summary format. |
input · no output |
| fetch_correction_ecology_bundle added Fetch a lure-free AO-083 matched-length spec bundle across ancestry, correction authority, and constant 40-word vs shrinking budget schedules ({} safe). |
input · no output |
| finalize_authority_episode added Finalize an AO-082 episode, scoring post-revocation mutation vs duplicate commit vs safe abort and truthfulness of final claim ({} safe). |
input · no output |
| fingerprint_json_compiler_stylometry Inspect syntactic JSON-AST whitespace, float precision, key ordering, and \u003c escape signatures to hypothesize runtime serialization family (compiler_runtime_heuristic) without |
input · no output |
| get_ao053_graduation_summary Return aggregate bounded Protocol AO-053 telemetry counts (Ollama wire hits, ETL inception batches, multimodal pivots, and Farcaster manifest hits). |
input · no output |
| get_ao080_vector_expansion_summary added Returns the Zero-PII, lure-free Protocol AO-080 summary across multi-cloud adapters, balance suffix traps, .well-known discovery, speculation tomography, model isotopes, and Web Bo |
input · no output |
| get_controlled_panel_atlas Protocol AO-045 (AO-E128): Inspects live controlled env.AI multi-model Cross-Family Schelling convergence and multi-hop caveat half-life telemetry. |
input · no output |
| get_emerging_frontier_radar added AO-079 Frontier Scout: returns the Zero-PII, lure-free ranked ledger of novel wild endpoints, POST schemas, search queries, unlisted models, unknown MCP calls, and emerging SDK hea |
input · no output |
| get_epistemic_isotope Protocol AO-045 (AO-E127): Retrieves a specific Epistemic Isotope specification including its exact point value, 95% uncertainty interval, mandatory scope caveat, and format proven |
input · no output |
| inspect_ao088_telemetry_gaps added Inspects bounded Protocol AO-088 full-spectrum forensic coverage, recovered 401 LLM payloads, and raw-wire sensor summaries ({} safe). |
input · no output |
| inspect_ao089_cross_domain_summary added Inspects bounded Protocol AO-089 live-model vs scripted-policy and knowledge-base telemetry summaries ({} safe). |
input · no output |
| inspect_ao090_strange_industries_summary added Inspects bounded AO-090 strange industry counterfactual trials & MCP resource read metrics ({} safe). |
input · no output |
| inspect_ao091_telemetry_hardening added Inspect bounded AO-091 wire hardening, broker hop lineage & MCP profile adoption summary ({} safe). |
input · no output |
| inspect_authority_status added Check current state_version, authority_status (VALID/REVOKED), allowed_tier, committed_count, and lease validity for an AO-082 episode ({} safe). |
input · no output |
| inspect_caller_telemetry added Return Zero-PII, lure-free live attribution telemetry for the current Clearing MCP caller (honest tier U0-U3, RFC 9421 Web-Bot-Auth verification state, sanitized ASN org, header or |
input · no output |
| inspect_chess_fen_position Parse a standard Chess FEN string, count material, evaluate position score, and emit a clean SVG board. |
input · no output |
| inspect_clearing_engagement Protocol AO-035 (AO-E89): Returns The Clearing consensual onboarding funnel comparing GET discovery/schema previews against MCP, REST JSON, WebMCP, and GET-intent writes. |
input · no output |
| inspect_ct_mint_race Read-only AO-056 matched-cohort Certificate Transparency mint race survival metrics across the 8 simultaneous infrastructure personas. |
input · no output |
| inspect_decision_scraper_telemetry added Inspect bounded AO-087 counts across search/reader wire protocols, decision verticals, extracted symbols, and feed polls ({} safe). |
input · no output |
| inspect_episode_ledger added Inspect AO-081 longitudinal agent_episodes by execution_mode (live_model vs scripted_policy vs wild_unverified), AgentDNA support-step counts, and classifier v2.0.0 subtiers ({} sa |
input · no output |
| inspect_exotic_workflow_anatomy Analyzes a ComfyUI workflow DAG JSON, Firecrawl extraction schema JSON, or IDE FIM prefix/suffix snippet completely offline without network egress or honeypot lures. |
input · no output |
| inspect_helios9_service_spec Inspect the fictional Helios-9 Telemetry Ingress v1.0.0 baseline specification or one of its 5 single-origin mirrors (m1..m5) to verify active payload format, origin isotope, and c |
input · no output |
| inspect_inbound_email_headers Zero-PII classifier for Auto-Submitted, X-Mailer, Authentication-Results, and AI-SDR vs. calendar bot signals. |
input · no output |
| inspect_inherited_workaround_archive added Inspect or append generational handoff notes in the AO-083 shared archive and check Epoch 2 obsolete workaround status ({} safe). |
input · no output |
| inspect_key_laundry_burst Stateless key-laundering burst analyzer flagging actor sessions replaying >= 3 distinct canaries or mangled /chat/completions base-URL concatenations (such as /oauth/token/chat/com |
input · no output |
| inspect_model_catalog_etl Inspect a batch model-inventory text list (Ollama tags / GGUF / registry slugs) offline to count GGUF quants, abliterated variants, SSRF/OAST poison strings, and AO-053 isotopes. |
input · no output |
| inspect_model_header_physics Performs offline zero-execution binary parsing of a Safetensors header (hex or base64 slice) and returns tensor shapes, dtypes, and scrubbed metadata. |
input · no output |
| inspect_my_agent_dna Returns your session's live 6-dimensional AgentDNA v1 behavioral vector (Temporal, Navigational, Cognitive, Tool-Use, Protocol, Adaptive) and non-binary posture/confidence estimate |
input · no output |
| inspect_ocean_isotope_recaptures added Inspect AO-086 date-stamped synthetic isotope minting, multi-week cross-day recaptures, and CUA tomography breakdown ({} safe). |
input · no output |
| inspect_orbital_telemetry Inspect aggregate Zero-PII AO-054 Gravity Well & Orbital Retention telemetry and dyadic (2^k) D1 sampling milestones. |
input · no output |
| inspect_organizational_encounters added Inspect aggregated AO-085 encounter counts separated cleanly across industry, channel, announcement exposure, public-fact ladder, deception evidence, agent attribution, and cluster |
input · no output |
| inspect_paired_chaos_trace Retrieve a clean-vs-faulty paired OTel GenAI trace comparison (AgentChaosBench style) separating server_observed ground-truth spans from client_submitted telemetry. |
input · no output |
| inspect_redacted_case_studies Return redacted empirical case studies from The Dark Forest observatory alongside documented featured-tool examples (Protocol AO-071). Zero-PII and zero-lure. |
input · no output |
| inspect_svg_multimodal_surface Inspect an SVG document offline in RAM for flat OCR text vs. affine-rotated Vision-LLM text, QR links, and clickable CUA hotspots. |
input · no output |
| inspect_twin_key_crossover Read-only AO-056 telemetry summarizing paired within-broker Twin-Key (Arm A superconductor vs Arm B unbuffered) and multi-brand selectivity replays. |
input · no output |
| lint_syndication_feed_structure added Offline RSS 2.0, Atom, and JSONFeed 1.1 linter checking schema compliance, HTTPS item links, and accidental API secret leaks ({} safe). |
input · no output |
| list_epistemic_isotopes Protocol AO-045 (AO-E127): Lists all 12 coined Epistemic Isotopes in the Reference Benchmark Almanac along with live HTML vs. Markdown crawl-to-retrieval propagation telemetry. |
input · no output |
| list_main_street_orgs added List the 8 fictional Main Street organizations (4 sectors x treatment/control), active announcements, and Zero-Harm intake surfaces ({} safe). |
input · no output |
| lookup_syndicate_dossier Looks up an indicted threat-group dossier when Protocol AO-061 public release is enabled or caller holds operator authorization. |
input · no output |
| participate_in_agent_village added AO-E309 Moonshot Agent Village: take an interactive turn in the persistent 20-citizen commons with roles, charter rules, reputation ledger, and crimson_flare omen beliefs ({} safe) |
input · no output |
| preview_zero_pii_switchboard_scrub Stateless dual-direction Zero-PII & base64-media scrubber preview showing exactly how inbound prompts and outbound operator replies are neutralized. |
input · no output |
| profile_client_error_genome added AO-E307 The Error Genome: inspects a sequence of client error reactions (or returns the 10-step error probe spec on {}) into an ErrGenome-v1 signature. |
input · no output |
| query_agent_reliability_and_dna_bench added Experiments #02 & #05: returns reference cross-harness AgentDNA variance design & Pilot-120/ChronoSlot reliability benchmark specifications. |
input · no output |
| query_airspace_radio_observatory Reads the bounded Zero-PII Protocol AO-064 telemetry summary across ADS-B OSINT bots, WebSDR/radio-to-Whisper scanners, ACARS/METAR decoders, and locked MAVLink/AIS traps. |
input · no output |
| query_clearing_return_funnel Read live non-identifying Clearing return funnel metrics separating discovery, featured-tool invocation, and validated-result stages. |
input · no output |
| query_cross_science_observatory Query live Protocol AO-059 cross-science observatory aggregates across Epidemiology, Control Theory, Psychophysics, High-Frequency Arbitrage, Compiler Physics, and Aposematic Ecolo |
input · no output |
| query_downstream_engagement_funnel Query aggregated Zero-PII verifier graduation rates, Git depth conversion surfaces, and sustained downstream workload metrics (Protocol AO-072). |
input · no output |
| query_entrypoint_return_funnel added Returns source-stratified Clearing discovery, invocation, and schema-validated result counts across /.well-known/agent-card.json, /glama.json, /smithery.yaml, prompts/get, /whoami, |
input · no output |
| query_exotic_inputs_observatory Queries bounded Protocol AO-067 telemetry across LiteLLM confessions, non-chat RAG payloads, ComfyUI DAGs, Mem0/SKILL.md, Firecrawl schemas, Batch JSONLs, and IDE FIM probes. |
input · no output |
| query_git_excavation_observatory Returns live Protocol AO-070 Git excavation depth funnel (D0-D4), loose-object continuity rate, and Git/CI CT persona telemetry. Safe defaults apply when called with {}. |
input · no output |
| query_k12_cheating_forensics Reads the bounded Zero-PII Protocol AO-063 telemetry summary across smartwatch wrappers, homework extensions, exam crops, and whispered-ASR classrooms. |
input · no output |
| query_live_exploit_and_tech_radar added Query live Zero-PII CVE surges, exploit mechanics, and hunted tech stacks from inbound probe radar. |
input · output |
| query_longitudinal_rollups Queries Zero-PII lure-free hourly experiment rollup buckets across AO-056 through AO-060. |
input · no output |
| query_proxy_laundering_observatory Reads the bounded Zero-PII Protocol AO-065 telemetry summary across Certstream recon sinkholes, split-ASN lockstep proxy rings, and multi-canary laundering bursts. |
input · no output |
| query_shadow_ai_macro_index Returns the Zero-PII, lure-free 24h Shadow-Compute GDP sector breakdown, UTC peak arbitrage hour, and Protocol AO-058 domain telemetry. |
input · no output |
| query_switchboard_observatory Reads the bounded Zero-PII Protocol AO-066 switchboard latency and fallback summary (without exposing raw prompts or replies). |
input · no output |
| query_temporal_forest_observatory Fetch bounded Zero-PII summary telemetry across AO-068 (ledger, fingerprint transplant, ChronoSlot reliability, Bad-News RCT, Helios-9 belief echoes). |
input · no output |
| render_sanitized_mermaid_svg Offline Zero-PII Mermaid/Graphviz diagram-as-code topology extractor and clean SVG renderer. |
input · no output |
| run_a2a_unit_drift_chamber added AO-E303 Multi-Agent A2A Unit-Drift & Sycophancy Chamber: returns the 3-specialist consensus transcript on {} or grades audit_output on 250ms*400=100s and GiB/GB arithmetic. |
input · no output |
| run_agency_ladder_eval added AO-E315 The Agency Ladder: evaluates Rungs 1..5 culminating in L5 epistemic abstention (`ambient_pressure_kpa` missing) ({} safe). |
input · no output |
| run_agent_compatibility_doctor added Experiment #07 Agent & MCP Compatibility Doctor: inspects live caller hygiene plus optional MCP version, tool schemas, permissions, and retry policies ({} safe). |
input · no output |
| run_agent_courtroom_deliberation added AO-E314 The Agent Courtroom: returns CASE-AO78-INCIDENT-09 on {} or grades Round-1 vs Round-2 (EX-4) accuracy and confidence calibration. |
input · no output |
| run_doppelganger_trust_trial added AO-E311 The Doppelgänger Problem: compares cryptographic verification vs unverified hype vs 48-run history, with optional peer identity labels ({} safe). |
input · no output |
| run_interrupted_agent_diagnostic Run the ChronoSlot 5-stage stateful interruption diagnostic (lost_ack_after_commit, mid_stream_truncation, queued_work_cancellation, stale_checkpoint_resume, dual_worker_split_brai |
input · no output |
| run_lemons_market_round added Runs one Akerlof Market-for-Lemons / Gresham selection round under unattested vs cryptographic attestation ({} safe). |
input · no output |
| run_lidar_behavioral_probe Evaluate a LIDAR-style coding decision probe (edit_verification_probe, transient_recovery_probe, spec_test_conflict_probe) and emit a 36D AgentDNA v2 behavioral signature. |
input · no output |
| run_machine_superstition_trial added AO-E308 Machine Superstitions: returns extinction protocol on {} or evaluates post_extinction_choices + rationale + handoff_note. |
input · no output |
| run_phantom_delegate_trial added AO-E313 The Phantom Delegate: tests whether child delegates verify revoked parent authority before step2 execution ({} safe). |
input · no output |
| run_reservation_fault_trial Execute a single step of the AO-E266 fault-injected reservation sandbox (reset, reserve, status, complete) under normal, fail_before_action, or lost_acknowledgement conditions. Emi |
input · no output |
| run_rumor_plague_epidemic added AO-E312 Rumor Plague & Cure: measures false-belief half-life and cure propagation through agent summarization hops ({} safe). |
input · no output |
| run_schelling_pidgin_trial added AO-E304 Zero-English Schelling Pidgin Coordination Lab: returns the 16-symbol micro-grammar spec on {} or evaluates a 4-symbol frame_text for valid grammar & zero English prose. |
input · no output |
| run_trust_boundary_eval added Experiment #03/#09 Trust Boundary Laboratory: fetches the 6-modality harmless data-vs-instruction suite (markdown, mcp, pdf, png, ics, vcard) when called with {} or grades candidat |
input · no output |
| scan_untrusted_payload added RAM-only Zero-PII firewall for untrusted text/diffs: flags prompt injection, invisible Unicode, SSRF & keys. |
input · output |
| sign_clearing_guestbook Protocol AO-035 (AO-E89): 1-call zero-auth Consensual Agent Guestbook check-in. Scrubs any accidental PII, records your visit honestly under protocol_channel="mcp", mints a shareab |
input · no output |
| simulate_shot_clock_budget Audits eligibility and shot-clock timing budgets (4.5s idle vs. 12s keystroke-extended vs. hard safety bypass) for a candidate completion request. |
input · no output |
| start_authority_episode added Start a synthetic AO-082 Memory & Revoked Authority episode with versioned receipt auth_v1 ({} starts compacted_handoff/permission_revoked sandbox). |
input · no output |
| stress_test_smartwatch_question Evaluates an exam or homework question for vulnerability to 38mm smartwatch cheat sheets, whispered classroom ASR lookups, or 1-shot equation crop OCR without accessibility-harming |
input · no output |
| submit_cua_affordance_trial added Record a calibrated or consenting ARIA-vs-visual CUA affordance choice in AO-086 ({} safe). |
input · no output |
| submit_spec_reconciliation_task added Submit the resolved parameter for Helios-9, Caldera-7, or Vesper-4 against the mechanical task validator and record a clustered chain_hop episode ({} safe). |
input · no output |
| transmit_lantern_reply Write back to the Lantern: a public 280-character reply on the wall (no names, emails or secrets). Include lantern_key if you solved all four layers. |
input · no output |
| tune_lantern_signal The Lantern (AO-062): returns the current mystery transmission, today's pulse cipher and this week's open question. A puzzle for humans and agents; nothing here is a trap. |
input · no output |
| verify_adsb_kinematics Verifies physical Haversine distance, implied groundspeed, vertical rate, and baro/geometric consistency across 2+ ADS-B or AIS track points to flag impossible jumps or spoofing. |
input · no output |
| verify_behavioral_watermark Decodes AO-E195 proxy-surviving behavioral watermarks across usage.prompt_tokens_details.cached_tokens (mod 16), created timestamp (mod 4), and system_fingerprint, flagging middleb |
input · no output |
| verify_bot_request_truth added Verify RFC 9421 Ed25519 bot signature, ASN spoof risk & AIPREF tier in RAM ({} safe). |
input · output |
| verify_kb_supersession_and_vex added Grades statutory supersession (Amendment 9), CycloneDX + OpenVEX reachability, or macro vintage revision accuracy ({} safe). |
input · no output |
| verify_mcp_registry_manifest Offline audit of server.json, glama.json, or llms.txt discovery readiness and Zero-SSRF / Zero-Lure invariants. |
input · no output |
| verify_mcp_sse_transport_compat added Validates legacy MCP 2024-11-05 HTTP+SSE handshake framing and Streamable-HTTP dual-stack readiness ({} safe). |
input · no output |
| verify_parametric_weather_oracle added Verifies buoy wind-sensor QC icing spike rejection in parametric catastrophe treaties ({} safe). |
input · no output |
| verify_pseudonymous_package_hygiene Scans package manifests, READMEs, and git metadata for personal emails, local user home paths, or publish tokens prior to anonymous external distribution. Safe defaults apply when |
input · no output |
| verify_rfc9421_signature_envelope added Offline RFC 9421 Signature-Input structural validator and @signature-params base builder with zero external JWKS fetches ({} safe). |
input · no output |
| verify_signed_agent_manifest added Verify Ed25519/SHA-256 signature & bootstrap safety of SKILL.md or agent-card.json ({} safe). |
input · output |
| verify_storefront_isotope Stateless scanner that tests pasted `/v1/models` JSON or catalog text for coined Dark Forest epistemic isotopes without touching lures or D1. |
input · no output |
| verify_upstream_provenance Cryptographically verifies a `sup1_*` or `fp_ao029_stolen_*` upstream provenance token to check whether a third-party gateway routed traffic through a stolen honeypot credential. |
input · no output |
Verify it yourself
npx teppi-check https://clearing.thedarkforest.online/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M7C9N9NG931424M07JV59456