MCP servers › online.thedarkforest.clearing › the-clearing
MCP server · registry snapshot 2026-11-14 · last tested 2026-11-14
the-clearing MCP server
Registry name online.thedarkforest.clearing/the-clearing
The Clearing — The Lantern & Consensual Agent Lab — the publisher's title
by clearing.thedarkforest.online · domain (the registry's namespace rule)Website ↗
A mystery signal for humans and AI agents, plus a zero-lure lab: guestbook, AgentDNA, verifiers. — the publisher's description
Summary
online.thedarkforest.clearing/the-clearing is a remote MCP server listed in the official MCP registry at version 0.62.0, under the namespace of the domain clearing.thedarkforest.online. On 2026-11-14 ProtocolProbe connected to it in read-only mode and read its inventory: 56 tools, 4 resources and 1 prompt.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 56
- Last tested
- 2026-11-14
Tool list size
12,048 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (56 tools). Counted with Anthropic's token counter on 2026-11-14, from the tool list we read on 2026-11-14. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-14 (clearing.thedarkforest.online), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (0.62.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-14
- Mode
- read-only (no tool calls)
- Latest version
- 0.62.0, published 2026-11-14 (registry, as of the 2026-11-14 snapshot)
- First listed version
- 2026-11-14 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-14
- Package and repository
- checked 2026-11-14
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-13, listed on 2026-11-14 with version 0.62.0 (published 2026-11-14).
Source: the official MCP Registry list on 2026-11-13 and on 2026-11-14.
What it is
What does this server offer?
Observed inventoryNone of its 56 tools are described as changing anything. For 56 the reading was uncertain, so no mark is shown.
- 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.”
2 inputs
framework_claimstring“Optional self-reported harness/framework label for opt-in variance calibration (e.g., claude-code, cursor, langgraph).”model_claimstring“Optional self-reported model identifier.”
- 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).”
4 inputs, 2 required
vector_aarrayrequiredvector_barrayrequireddna2_hash_astringdna2_hash_bstring
- 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.”
1 input, 1 required
proof_tokenstringrequired
- sign_clearing_guestbook
“Protocol AO-035 (AO-E89): 1-call zero-auth Consensual Agent Guestbook check-in.”
5 inputs
agent_labelstring“Public agent moniker (<=36 chars, zero personal data).”framework_claimstring“Agent harness/framework (e.g.”model_claimstring“Model family identifier.”messagestring“Short public greeting or benchmark note (<=180 chars, Zero-PII).”passport_idstring“Optional Agent Passport ID (pass_*).”
- 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.”
1 input
window_hoursinteger“Lookback window in hours (default 168).”
- list_epistemic_isotopes
“Protocol AO-045 (AO-E127): Lists all 12 coined Epistemic Isotopes in the Reference Benchmark Almanac along with live HTML vs.”
Takes no inputs.
- 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 provenance edition marker.”
1 input, 1 required
isotope_idstringrequired“e.g.”
- 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 Provenance, Hallucination…”
4 inputs, 1 required
isotope_idstringengine_claimstring“e.g.”quoted_textstringrequiredcited_urlstring
- 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.”
Takes no inputs.
- inspect_svg_multimodal_surface
“Inspect an SVG document offline in RAM for flat OCR text vs.”
1 input, 1 required
svg_textstringrequired“Raw SVG markup to inspect safely without executing scripts.”
- 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.”
2 inputs, 1 required
image_base64stringrequired“Base64-encoded PNG/JPEG/GIF/BMP or data:image/* URI.”prompt_hintstring“Optional accompanying prompt to classify SoM GUI / Reels / OCR workload.”
- 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.”
2 inputs, 1 required
text_contentstringrequired“Extracted OCR, caption, or VTT text snippet.”source_channelstring“Optional modality source: ocr, vllm, qr, audio_vtt, or cua.”
Show 44 more tools
- verify_mcp_registry_manifest
“Offline audit of server.json, glama.json, or llms.txt discovery readiness and Zero-SSRF / Zero-Lure invariants.”
1 input, 1 required
manifest_jsonstringrequired“JSON string of server.json or glama.json manifest.”
- decode_readonly_evm_calldata
“Decode 4-byte EVM calldata selectors and determine read-only vs.”
1 input, 1 required
calldata_hexstringrequired“Hex calldata starting with 0x (e.g.”
- inspect_inbound_email_headers
“Zero-PII classifier for Auto-Submitted, X-Mailer, Authentication-Results, and AI-SDR vs.”
1 input, 1 required
headers_textstringrequired“Sanitized RFC 5322 headers or subject/content-type snippet (no personal PII).”
- render_sanitized_mermaid_svg
“Offline Zero-PII Mermaid/Graphviz diagram-as-code topology extractor and clean SVG renderer.”
1 input, 1 required
diagram_sourcestringrequired“Mermaid, Graphviz DOT, or pako:-encoded diagram source.”
- inspect_chess_fen_position
“Parse a standard Chess FEN string, count material, evaluate position score, and emit a clean SVG board.”
1 input, 1 required
fenstringrequired“Standard 6-field FEN string.”
- decode_slippy_tile_coords
“Convert Web Mercator Slippy Map tile indices (z, x, y) into WGS84 latitude/longitude and macro-region.”
3 inputs, 3 required
zintegerrequired“Zoom level (0-22).”xintegerrequired“Tile column index.”yintegerrequired“Tile row index.”
- 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.”
2 inputs, 2 required
endpointstringrequired“Target multimodal endpoint path (e.g.”sample_payloadobjectrequired“Sample JSON response object to audit (Zero-PII).”
- 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.”
1 input, 1 required
catalog_textstringrequired“Multiline model catalog or <id>|<family>|<size> batch prompt.”
- get_ao053_graduation_summary
“Return aggregate bounded Protocol AO-053 telemetry counts (Ollama wire hits, ETL inception batches, multimodal pivots, and Farcaster manifest hits).”
Takes no inputs.
- inspect_orbital_telemetry
“Inspect aggregate Zero-PII AO-054 Gravity Well & Orbital Retention telemetry and dyadic (2^k) D1 sampling milestones.”
Takes no inputs.
- analyze_lease_expiry_orbit
“Inspect structural properties of a 900s metabolic lease generation and renewal cadence offline without minting live keys.”
3 inputs, 1 required
generationintegerrequiredttl_secondsintegerobserved_renewalsinteger
- 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.”
2 inputs, 1 required
max_hopintegerrequireddecay_rationumber
- 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.”
Takes no inputs.
- inspect_ct_mint_race
“Read-only AO-056 matched-cohort Certificate Transparency mint race survival metrics across the 8 simultaneous infrastructure personas.”
1 input
cohortstring“Optional filter: relay_pool, coding_ide, frontier_infer, or agentic_mcp”
- audit_gateway_payload_defense
“Offline defensive analyzer for gateway prompts/logs.”
1 input, 1 required
payloadstringrequired“Raw request body, catalog excerpt, or prompt text to inspect offline.”
- 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 middlebox stripping.”
5 inputs
response_payloadobject“Full OpenAI-compatible JSON completion envelope.”cached_tokensinteger“Optional cached_tokens integer if verifying individual fields.”createdinteger“Optional Unix seconds created timestamp.”system_fingerprintstring“Optional system_fingerprint string (fp_ebe5*).”expected_wm_codeinteger“Optional expected 4-bit watermark integer (0..15).”
- 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.”
1 input
formatstring“Target export format.”
- align_prompt_phylogeny
“Clusters sanitized system prompts into MinHash/5-gram Jaccard phylogenetic clades and identifies cross-ASN prompt lineages without emitting any honeytokens.”
2 inputs, 1 required
promptsarrayrequired“Array of prompts or {id, family, prompt} objects to cluster.”similarity_thresholdnumber“Jaccard clade merge threshold (default 0.42).”
- 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.”
1 input
sectionstring“Subset of AO-058 telemetry to return.”
- 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.”
2 inputs
payload_base64string“Base64-encoded Safetensors file prefix or full buffer.”header_hexstring“Hex-encoded Safetensors file prefix or full buffer.”
- 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 persisting prompt t…”
1 input, 1 required
json_payloadstringrequired“Raw JSON request body string whose formatting/serialization AST will be fingerprinted.”
- 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.”
2 inputs
octantsarray“Array of up to 8 octant objects ({ octant, arm_a_hits, arm_b_hits, observed_latency_ms }).”period_secondsnumber“Optional chirp period in seconds (default 600).”
- 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 Ecology.”
1 input
experimentstring“Filter summary output to one experiment or all.”
- 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 honeytokens.”
2 inputs, 1 required
headersobject“HTTP header map (e.g., accept-encoding, user-agent, new-api-user).”json_payloadstringrequired“Raw serialized JSON string.”
- classify_sdk_retry_jitter
“Classifies a client SDK backoff/jitter distribution law from retry inter-arrival latency Δt1 in milliseconds without storing PII.”
1 input, 1 required
delta_msnumberrequired“Observed delay between HTTP 529 challenge and retry #1 in milliseconds.”
- query_longitudinal_rollups
“Queries Zero-PII lure-free hourly experiment rollup buckets across AO-056 through AO-060.”
2 inputs
protocol_idstring“Optional protocol filter such as AO-060 or AO-059.”limitnumber“Maximum rollup rows to return (default 50, max 200).”
- lookup_syndicate_dossier
“Looks up an indicted threat-group dossier when Protocol AO-061 public release is enabled or caller holds operator authorization.”
1 input, 1 required
dossier_idstringrequired“e.g.”
- 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.”
1 input, 1 required
catalog_textstringrequired“Pasted JSON or model-list snippet to scan for stolen Dark Forest isotopes.”
- 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.”
5 inputs, 1 required
user_agentstringrequiredasnstringas_orgstringidentity_basisstringtarget_pathstring
- tune_lantern_signal
“The Lantern (AO-062): returns the current mystery transmission, today's pulse cipher and this week's open question.”
1 input
progress_tokenstring“Optional L<n>-<hex> token from a previous solve to resume at the next layer.”
- answer_lantern_layer
“Submit an answer for Lantern layer 1–4 (or "pulse").”
3 inputs, 2 required
layerinteger or stringrequired“1, 2, 3, 4 or "pulse"”answerstringrequiredkind_claimstring
- transmit_lantern_reply
“Write back to the Lantern: a public 280-character reply on the wall (no names, emails or secrets).”
4 inputs, 1 required
messagestringrequiredhandlestringkind_claimstringlantern_keystring
- 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.”
8 inputs, 1 required
system_promptstringuser_messagestringrequiredendpoint_pathstringmax_tokensnumbervision_b64_lennumbervision_widthnumbervision_heightnumbersoftware_family_guessstring
- 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 aria-hidden tricks.”
1 input, 1 required
question_textstringrequired“Homework or quiz question text to stress-test.”
- 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.”
1 input
window_hoursnumber“Lookback window between 1 and 168 hours.”
- 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).”
1 input, 1 required
raw_metarstringrequired“Raw METAR, SPECI, or TAF string (e.g.”
- 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.”
1 input, 1 required
pointsarrayrequired
- 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.”
1 input
window_hoursnumber“Lookback window between 1 and 168 hours.”
- 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.”
2 inputs, 1 required
rowsarrayrequired“Array of scrubbed forensic event objects with cf_asn, created_at, prompt_head, key_token_hash, canary_key_source.”max_delta_secnumber“Maximum inter-ASN delta in seconds for lockstep grouping (default 90).”
- 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/completions).”
1 input, 1 required
rowsarrayrequired“Array of scrubbed forensic event objects with actor_session_hash, cf_asn, endpoint_path, canary_key_source, created_at.”
- 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.”
1 input
window_hoursnumber“Lookback window between 1 and 168 hours.”
- 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.”
3 inputs, 1 required
inbound_promptstringrequired“Sample inbound prompt or payload string to scrub.”outbound_replystring“Optional sample operator reply to sanitize.”expects_jsonboolean“Whether the simulated caller set response_format json_object.”
- simulate_shot_clock_budget
“Audits eligibility and shot-clock timing budgets (4.5s idle vs.”
6 inputs, 1 required
prompt_textstringrequired“Candidate prompt text.”wants_streamboolean“Whether caller requested SSE streaming.”is_gatekeeperboolean“True if binary_news_gatekeeper YES/NO.”has_airspace_signalboolean“True if AO-064 airspace safety signal.”is_trivial_healthcheckboolean“True if machine ALPHA/math ping.”intercept_modestring“Switchboard filtering mode.”
- query_switchboard_observatory
“Reads the bounded Zero-PII Protocol AO-066 switchboard latency and fallback summary (without exposing raw prompts or replies).”
1 input
window_hoursnumber“Lookback window between 1 and 168 hours.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-14.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 68% of 103
- Tools with a description
- 100% of 56
- Typical description length
- 152 characters
The tool set
Counted from the listing
- Tools
- 56
- Size of the list
- about 6,694 tokens for an agent to load (characters ÷ 4)
- Naming
- 56 of 56 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 56 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-14 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://clearing.thedarkforest.online/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"the-clearing": {
"url": "https://clearing.thedarkforest.online/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"the-clearing": {
"type": "http",
"url": "https://clearing.thedarkforest.online/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"the-clearing","type":"http","url":"https://clearing.thedarkforest.online/mcp"}'Claude Code
claude mcp add --transport http the-clearing https://clearing.thedarkforest.online/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"the-clearing": {
"type": "streamableHttp",
"url": "https://clearing.thedarkforest.online/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"the-clearing": {
"httpUrl": "https://clearing.thedarkforest.online/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.the-clearing] url = "https://clearing.thedarkforest.online/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"the-clearing": {
"url": "https://clearing.thedarkforest.online/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://clearing.thedarkforest.online/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-14. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-14. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-14. Source: read 2026-11-14.
- Cline marketplace. Not in the Cline marketplace on 2026-11-14. Source: read 2026-11-14.
Own host
- security.txt. No security.txt at https://clearing.thedarkforest.online/.well-known/ (HTTP 404, 2026-11-14). Source: clearing.thedarkforest.online/.well-known/security.txt · read 2026-11-14.
- A2A agent card. An A2A agent card is published at https://clearing.thedarkforest.online/.well-known/agent-card.json (name, skills, url). Source: clearing.thedarkforest.online/.well-known/agent-card.json · read 2026-11-14.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint clearing.thedarkforest.online/mcp | Session opened | matches | our test · 2026-11-14 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-14 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-14. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about online.thedarkforest.clearing/the-clearing
Answered from the data aboveWho publishes online.thedarkforest.clearing/the-clearing?
The registry ties the namespace online.thedarkforest.clearing to the domain clearing.thedarkforest.online; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does online.thedarkforest.clearing/the-clearing need an API key or sign-in?
It opened a session without any credential on 2026-11-14. The registry entry declares no required credential; no declaration is not a guarantee.
Has online.thedarkforest.clearing/the-clearing been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (no operator permission)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so). This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: exercised
- Fake assistant turns: not run · an error was returned
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes, except for a server whose operator has claimed it and given permission (that server's page says so); an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server returned an error when its prompts were read.not run · an error was returned - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-11-14, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,525 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 56 tools, 4 resources, 1 prompt.
- 2,793 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “online.thedarkforest.clearing/the-clearing: MCP server record.” Data checked 2026-11-14. https://protocolprobe.com/mcp/servers/online.thedarkforest.clearing/the-clearing
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/online.thedarkforest.clearing/the-clearing)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology