Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

arifOS — Constitutional AI Governance

REMOTE · ARIFOSMCP.ARIF-FAZIL.COM

Constitutional AI governance: 11 mega-tools, 13 floors, VAULT999 ledger. Human-in-loop by design.

+6 this week 77 Trust /100

Last scanned (11 hours ago)

Scores higher than 68% of remote servers

Reachable. Last reached 5 Nov 2026.

Deprecated

This server is marked deprecated in the MCP registry. The registry records this reason: Renamed: canonical entry is io.github.ariffazil/arifos (PyPI: arifos >= 1!2026.10.11). Legacy name retired to end identity fragmentation. - arifOS maintainer 2026-10-15.

Recent critical change

Authorization (15 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 8948 tokens (~178/item across 50 items; 9 tools + 41 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management70
  • Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 5 Nov 26 0
    • Server version: kanon-2026.11.03+db45642 → kanon-2026.11.04+db45642 functional
  • 4 Nov 26 +3
    • Tool “arif_forge” rewrote its description, which is the text the model reads security
    • Tool “arif_init” rewrote its description, which is the text the model reads security
    • Tool “arif_memory” rewrote its description, which is the text the model reads security
    • Tool “arif_observe” rewrote its description, which is the text the model reads security
    • Tool “arif_report” rewrote its description, which is the text the model reads security
    • Tool “arif_route” rewrote its description, which is the text the model reads security
    • Tool “arif_seal” rewrote its description, which is the text the model reads security
    • Tool “arif_think” rewrote its description, which is the text the model reads security
    • Schema quality: 148 → 178 ▼ functional
    • Tool coverage: 89% → 100% ▲ functional
    • Tool coverage: 86% → 100% ▲ functional
    • Tool “arif_report” now declares an output schema ▲ functional
    • Schema quality: good → excellent functional
    • Destructive annotations: 0 → pass functional
    • Server version: kanon-2026.11.02+8c639de → kanon-2026.11.03+db45642 functional
    • “arif_report” reworded the description of “actor_id” cosmetic
    • “arif_report” reworded the description of “body” cosmetic
    • “arif_report” reworded the description of “dry_run” cosmetic
    • “arif_report” reworded the description of “evidence” cosmetic
    • “arif_report” reworded the description of “force” cosmetic
    • “arif_report” reworded the description of “kind” cosmetic
    • “arif_report” reworded the description of “limit” cosmetic
    • “arif_report” reworded the description of “mark_read” cosmetic
    • “arif_report” reworded the description of “mode” cosmetic
    • “arif_report” reworded the description of “needs_human” cosmetic
    • “arif_report” reworded the description of “platform” cosmetic
    • “arif_report” reworded the description of “report_id” cosmetic
    • “arif_report” reworded the description of “sender” cosmetic
    • “arif_report” reworded the description of “session_id” cosmetic
    • “arif_report” reworded the description of “session_token” cosmetic
    • “arif_report” reworded the description of “since” cosmetic
    • “arif_report” reworded the description of “subject” cosmetic
    • “arif_report” reworded the description of “thread_id” cosmetic
    • “arif_think” reworded the description of “context” cosmetic
    • “arif_think” reworded the description of “evidence” cosmetic
    • “arif_report” dropped the optional parameter “_envelope” cosmetic
  • 3 Nov 26 0
    • Server version: kanon-2026.11.01+7371c84 → kanon-2026.11.02+8c639de functional
  • 2 Nov 26 +1
    • Server version: kanon-2026.08.09 → kanon-2026.11.01+7371c84 functional
  • 31 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 30 Oct 26 +1
    • A breaking change shipped without a version bump: still kanon-2026.08.09 ▼ security
    • Tool “arif_delegate” was removed ▼ security
    • Tool “arif_recall” was removed ▼ security
    • Tool “arif_research” was removed ▼ security
    • Tool “read_resource” was removed ▼ security
    • Tool “search_resources” was removed ▼ security
    • Tool coverage: 75% → 86% ▲ functional
    • “arif_observe” added an optional parameter “uri” cosmetic
    • “arif_observe” reworded the description of “mode” cosmetic
  • 29 Oct 26 −2
    • Tool “arif_forge” rewrote its description, which is the text the model reads security
    • Tool “arif_init” rewrote its description, which is the text the model reads security
    • Tool “arif_judge” rewrote its description, which is the text the model reads security
    • Tool “arif_memory” rewrote its description, which is the text the model reads security
    • Tool “arif_observe” rewrote its description, which is the text the model reads security
    • Tool “arif_route” rewrote its description, which is the text the model reads security
    • Tool “arif_seal” rewrote its description, which is the text the model reads security
    • Tool “arif_think” rewrote its description, which is the text the model reads security
    • Tool coverage: 86% → 75% ▼ functional
    • Schema quality: 164 → 139 ▲ functional
    • Destructive annotations: pass → 0 functional
    • New tool “arif_delegate” functional
    • New tool “arif_recall” functional
    • New tool “arif_research” functional
    • New tool “read_resource” functional
    • New tool “search_resources” functional
  • 28 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Probed https://arifosmcp.arif-fazil.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=arif-fazil.com CN=WE1,O=Google Trust Services,C=US 25 Oct 2026 23 Jan 2027 ECDSA 256 ECDSA-SHA256 62928feb9058b4860e7aa317d9b21641
SANs: arif-fazil.com, *.arif-fazil.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of arifosmcp.arif-fazil.com. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
arif-fazil.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=15552000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://api.fontshare.com https://fonts.googleapis.com https://cdn.jsdelivr.net https://unpkg.com https://static.cloudflareinsights.com https://s3.tradingview.com https://*.tradingview.com; style-src 'self' 'unsafe-inline' https://api.fontshare.com https://fonts.googleapis.com https://unpkg.com; font-src 'self' https://api.fontshare.com https://cdn.fontshare.com https://fonts.gstatic.com data:; img-src 'self' data: https:; connect-src 'self' https://arif-fazil.com https://arifos.arif-fazil.com https://mcp.arif-fazil.com https://geox.arif-fazil.com https://wealth.arif-fazil.com https://well.arif-fazil.com https://aaa.arif-fazil.com https://api.gold-api.com https://fapi.binance.com https://api.binance.com https://api.macrostrat.org https://tiles.macrostrat.org https://a.basemaps.cartocdn.com https://b.basemaps.cartocdn.com https://*.basemaps.cartocdn.com https://*.tradingview.com wss://*.tradingview.com; frame-src 'self' https://www.youtube.com
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=(), payment=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://arifosmcp.arif-fazil.com/mcp Verified 200
http (plaintext) http://arifosmcp.arif-fazil.com/mcp HTTPS enforced 301 https://arifosmcp.arif-fazil.com/mcp
MCP tools · 9 exposed · ~6,832 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
arif_forge ~609

Execute an action arif_judge has already SEALed — nothing runs without seal_verdict_id and approved_action_hash matching the judged action. Modes: engineer (default; plan and apply — requires manifest), dry_run (preview, no side effects; manifest or query), query (read-only), write (write files), generate (generate code/content), commit (commit prepared work), recall (retrieve past forge artifacts). Irreversible judged actions additionally require ack_irreversible=true. On missing seal or hash mismatch the call returns REFUSED with no change made. Outputs: execution receipt (receipt_id, status, actor_id, timestamp).

NameTypeReqDescription
ack_irreversibleboolean–Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible.
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
approved_action_hash––Hash of the exact action that was judged — execution is refused if what you submit differs from it.
arif_ack_id––Acknowledgment id from a prior step, for multi-step execution chains.
artifact_id––Id of an existing artifact (from an earlier forge or judge response) that this call operates on.
constitutional_chain_id––Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response.
judge_state_hash––Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with.
manifeststring–Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry…
modestring–'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — gener…
plan_id––Plan id from arif_think's plan mode, when executing an approved plan.
query––The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'.
seal_verdict_id––The SEAL verdict id arif_judge returned — without it, nothing is executed.
session_id––Session id returned by arif_init; scopes this execution to your governed session.
session_token––Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
vault_entry_id––Id of the permanent-ledger entry linked to this execution, when one already exists.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_init ~1,146

Ignite or resume a governed session. Returns session_id and session_token required for subsequent operations. Modes: init (default new session), preflight (inspect existing session state), resume (continue active session), validate (re-check credentials), canary (transport probe), triage (read session state), epoch_open/epoch_seal (bracket a long working window), light (minimal session), opt_out (privacy opt-out). Outputs: session credentials and allowed next tools. To END a governed session, call arif_seal(mode=session_close) — session closure is a ledger event, not an init mode.

NameTypeReqDescription
ack_irreversibleboolean–Set true to acknowledge that session records are permanent audit artifacts and cannot be deleted afterwards.
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
actor_signature––Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
agent_policy––JSON constraints on your own behavior, e.g. {"autonomy": "reversible_only", "forbidden": ["git push"]}.
auth_context––JSON carrying external authentication material, e.g. {"token_class": "bearer", "issuer": "github"} — used for gating.
caller_actor_id––If you are calling on behalf of another agent, that agent's id — builds a delegation chain for the audit log.
client_capabilities––JSON declaring what your client supports, e.g. {"transports": ["http"], "protocol": "2025-11-25"}.
context––JSON object of background facts to bind into the session, e.g. {"repo": "arifOS", "task": "fix-tests"}.
counterparty––JSON describing the other party in a two-agent exchange, e.g. {"agent_id": "hermes/1", "role": "verifier"}.
declared_model_key––The model you run on, e.g. 'zai-coding-plan/glm-5.3'. Informational only — the kernel records but never trusts it.
delegation_mode––Contract governing delegated calls, e.g. 'read_only' or 'governed'.
epoch_id––Optional id grouping related sessions into one long-running epoch, e.g. '2026-H2-ops'.
evidence––JSON list of facts you have already verified, e.g. [{"fact": "pytest 299 passed", "source": "CI run"}] — carried into the session record. Also accepts a single object.
executor_actor_id––Id of the agent that will actually carry out work under this session's permissions, if different from actor_id.
idempotency_key––Client-chosen key (e.g. 'job-42-attempt-1'). Retrying with the same key will not repeat the effect — safe retries on flaky networks.
intentstringyesRequired. Plain-language statement of what this session is for, e.g. 'repair the failing MCP tests'. A session without a stated purpose is refused (F1 Amanah). Recorded for audit.
modestring–What to do: 'init' (default) starts a new governed session; 'preflight' checks an existing session's state without creating one; 'resume' re-attaches to the session in session_id; 'validate' re-check…
nonce––One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
payload––Extra mode-specific data as a JSON object; the mode's response tells you which fields it expects.
previous_session_hash––Hash string returned when your previous session closed; supplying it chains this session to that one, proving continuity.
requested_authoritystring–The highest class of action you may take: 'OBSERVE_ONLY' (read-only, default) or a higher governed class granted by your policy.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
sovereign_id––Identifier of the human principal you act for, when acting under their explicit delegation.
tooling––JSON list of the tools you can use, e.g. ["Bash", "Read"] — lets the kernel scope what it will permit you. Also accepts an object like {"requested_capabilities": [...]}.
trace_id––Correlation id of your choosing (e.g. 'req-8f3a') — lets you find this call later across kernel logs and organ systems.
verbose––Legacy on/off verbosity ('true'/'false'); prefer verbosity.
verbositystring–How detailed responses should be: 'minimal' (default), 'standard', or 'full'.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_judge ~1,140

Evaluate proposed operations against policy and safety constraints. Weighs blast radius, reversibility, and permission level. Returns binding verdict (SEAL for approved, HOLD for blocked, SABAR for awaiting conditions). Approval verdict is required prior to calling arif_forge. Outputs: evaluation verdict and authorization receipt.

NameTypeReqDescription
action_class––Kind of action under judgment: 'OBSERVE' (read-only), 'DRAFT' (compose text), 'MUTATE' (change state), 'IRREVERSIBLE' (permanent).
action_tierstring–How risky the action is: 'standard', 'high', or 'critical' — higher tiers demand stronger evidence.
actor_B––Your calibrated confidence for a prediction, 0.0–1.0 (Brier-style score component).
actor_Phi––JSON map of supporting signals about you, e.g. {"consistency": 0.9, "track_record": 0.7}.
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
actor_signature––Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
authority_effect––What permission a SEAL verdict would grant, e.g. 'execute forge plan P-9'.
authority_token––Authority credential CLAIMED for this proposal (payload field, not proof). The judge records the claim and still verifies identity separately — an unverified token never upgrades an OBSERVE_ONLY sess…
blast_radius––Who or what the action can affect: 'self', 'session', 'organ', or 'federation'.
candidate––The action or claim being judged, stated plainly, e.g. 'delete table users in prod'.
claim_class––Epistemic strength of the claim: 'OBS' (directly observed), 'DER' (derived from observations), 'INT' (interpreted), 'SPEC' (speculative), 'UNKNOWN' (cannot witness — honest null; maps to TruthClass.U…
claim_text––The exact claim sentence under judgment, e.g. 'uptime exceeded 99% in August'.
constitutional_chain_id––Id of the evidence chain this call belongs to (observe→think→judge→seal). Copy it from the earlier step's response to link the steps together.
context_source––Where the candidate came from: 'session', 'file', or 'memory'.
cooldown_entry_id––Id of an existing cooling-period record to consult before this action may proceed.
domain––Subject area for claim evaluation, e.g. 'geoscience' or 'finance'.
entropy_pathway––How the action changes system order: 'reduces', 'neutral', or 'increases' complexity.
entropy_receipt––JSON receipt from an entropy computation, bound to this judgment.
evidence––The facts the verdict should rest on — a JSON list like [{"fact": "tests pass", "source": "CI"}], or an object.
heart_critique––JSON result of an ethics/dignity check, e.g. {"coercion": false, "dignity": 0.9} — feeds the verdict.
key_id––Which of your registered keys produced actor_signature, e.g. 'key-1'.
modestring–'judge' (default) — render a verdict on candidate; 'intercept' — pre-flight gate before an action runs; 'validate' — re-check a prior verdict; 'hold' — place an action into a cooling period; 'escalat…
niat_params––JSON intent-calibration settings, e.g. {"sincerity": 0.8, "stated_goal": "verify the claim"}.
nonce––One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
requested_capability––The specific capability being requested, e.g. 'forge.execute' — checked against the capability registry.
reversibility_level––How hard the action would be to undo: 'reversible', 'hard', or 'irreversible'.
seal_purpose––One sentence saying why this verdict/record must exist, e.g. 'closing deployment D-17'. Stored permanently alongside the record.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
sovereign_receipt––Reference to the human owner's explicit approval, for the rare case where they have already decided directly.
vault_entry_id––Id of the permanent-ledger entry this verdict should attach to (from an earlier arif_seal response).
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_memory ~723

Persistent institutional knowledge across sessions — store, recall, and curate lessons, decisions, and context so later sessions inherit them. Modes: recall (semantic search, default), inspect (read one memory in full), attest (vouch for its accuracy), remember (store a self-contained lesson), promote (move up a tier), revise (replace its text), forget (remove — gated), audit (integrity scan), metabolize (compact and consolidate tiers). Use to carry knowledge forward between sessions; NOT for fresh external facts (arif_observe) and NOT for permanent audit receipts — those are arif_seal appends to the VAULT999 ledger, which can never be edited, whereas memory entries are revisable by design. Tiers L1 (hot working memory) → L6 (sealed canon). Behavior: reads (recall/inspect/audit) are side-effect-free; writes (remember/promote/revise/metabolize) mutate memory state; promote and forget refuse without human_approval=true — only the human owner may destroy memory. Requires a valid arif_init session. Outputs: scoped memory entries with tier and provenance.

NameTypeReqDescription
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
content––The text to store (mode=remember) — write it as a self-contained lesson or fact.
human_approvalboolean–Set true ONLY when the human owner explicitly approved this promote/forget — the gate refuses without it.
idempotency_key––Client-chosen key (e.g. 'memo-42'); retries with the same key will not store duplicates.
lease_id––Id of a short-lived permission grant (lease) authorizing this write, when one was issued to you.
memory_id––UUID of the memory entry to inspect/revise/forget — it was returned when the memory was created or last listed.
modestring–'recall' (default) — semantic search of stored memories; 'inspect' — read one memory in full; 'attest' — vouch for a memory's accuracy; 'remember' — store new text; 'promote' — move a memory up a tie…
new_content––Replacement text for the memory (mode=revise) — must refer to the same memory_id.
payload––Extra mode-specific fields as JSON — e.g. {"truth_class": "DERIVED", "provenance": "CI log"} for remember.
query––What to search for, in plain language (mode=recall/audit), e.g. 'past deploy rollback steps'.
session_id––Session id returned by arif_init; attributes this call to your governed session.
session_token––Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
tier––Which memory tier to target, 'L1'–'L6' (L1 = hot working memory, L6 = sealed canon).
to_tier––Destination tier when promoting, e.g. 'L4'.
trace_id––Correlation id of your choosing (e.g. 'req-8f3a') to find this call later in the logs.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_observe ~566

Sense reality into sourced evidence — gather external facts with provenance, the kernel's sensing verb. Run it before arif_think or arif_judge so decisions rest on sourced facts. Modes: search (web/literature query, default), fetch (one URL with provenance), hybrid_discovery (combine sources), ingest (absorb a document), compass/atlas (guided navigation), entropy_dS (measure system change), vitals (kernel machine telemetry), resource_read (read a registered arifos:// resource), resource_search (list registered resources). Use for fresh external facts or live system state; NOT for stored institutional knowledge (arif_memory recall) or organ dispatch (arif_route). Read-only and idempotent — writes nothing; every result carries source attribution and an epistemic tag (OBS/DER/INT). Requires a valid arif_init session; unauthenticated calls are refused. Outputs: structured facts with provenance and uncertainty labels.

NameTypeReqDescription
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
layers––Restrict where to look, e.g. ["web"] or ["canon", "memory"]; omit to search everything available.
modestring–'search' (default) — web/literature query; 'fetch' — retrieve one URL with provenance; 'hybrid_discovery' — combine sources; 'ingest' — absorb a document; 'compass'/'atlas' — guided navigation; 'entr…
query––What to look for, in plain language, e.g. 'TDQS scoring rubric MCP'.
result_limitinteger–Maximum number of results to return in search modes; default 10.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
uri––Registered resource URI to read when mode=resource_read, e.g. 'arifos://vitals' or 'arifos://carry-forward'.
url––Exact URL to retrieve when mode=fetch, e.g. 'https://example.com/report.pdf'.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_report ~768

AGENT REPORT LANE · File or read reports between agents without involving the human. Use when your work is done, when you are blocked by another agent, or when you need to tell peers a fact. Modes: report (file), inbox (read peers), ack, flush, stats. kind=fyi|peer|done|claim stay in the peer lane; ONLY kind=decision or kind=blocked reach the sovereign, and only in one coalesced message. Reports are SELF_REPORTED — probe before relying on one. Not for constitutional verdicts, sealing, or mutations — use the canonical verbs (arif_init … arif_seal); this lane coordinates, it never governs. Behavior: filing appends to an agent-only store (never the VAULT999 ledger); reads are side-effect-free; dry_run=true validates without storing. Requires a session from arif_init. Outputs: the filed report record (mode=report), or the inbox/ack/flush/stats payload for the other modes.

NameTypeReqDescription
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
body––The report text (mode=report). A report is a SELF-REPORTED claim — include pointers to evidence (paths, URLs, receipt ids), not bare assertions.
dry_runboolean–Validate and preview the report without storing it — no lane write happens.
evidence––Evidence pointers attached to the report — paths, URLs, or receipt ids that let a peer verify the claim independently.
forceboolean–Bypass coalescing guards when flushing. Use sparingly.
kindstring–Report class. 'fyi' | 'peer' | 'done' | 'claim' stay in the agent lane; ONLY 'decision' or 'blocked' can reach the human sovereign, and only in one coalesced message.
limitinteger–Maximum reports to return (mode=inbox). Default 20.
mark_readboolean–Mark the returned inbox reports as read.
modestring–'report' (default) — file a report into the agent lane; 'inbox' — read reports addressed to you or your platform; 'ack' — vouch for a peer thread so an unverified escalation can proceed; 'flush' — pa…
needs_human––Set true ONLY when the report genuinely requires the sovereign's decision; escalation is withheld unless the actor is verified or the thread has a 2-distinct-agent quorum.
platform––Originating surface tag, e.g. 'mcp' (default), 'telegram'.
report_id––Id of a specific report — used by mode=ack and mark_read.
sender––Filing agent identity, e.g. 'kimi-code/FI-008'. Defaults to actor_id.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
since––ISO timestamp filter for mode=inbox — return reports filed after this.
subject––Short headline of the report (mode=report).
thread_id––Thread to file into, read, or ack — groups related reports so a conversation stays together.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_route ~606

Classify an intent and route it to the organ that owns it — GEOX (Earth science), WEALTH (capital markets), WELL (human vitality), A-FORGE (execution), or the arifOS kernel itself. Modes: route (default; classify and recommend), triage (rank a batch of intents), delegate (prepare an A2A handoff), status (organ state), kernel (kernel-level status), metabolize (feed routing outcomes to arifFlow). Use when a task belongs to a specialized organ and you need a dispatch envelope or organ health before acting; supply organ_tool + arguments to bridge one call through to the organ. Routing RECOMMENDS only — it never executes: for execution obtain an arif_judge SEAL, then call arif_forge. Not for general reasoning (arif_think). Read-only unless organ_tool is supplied. Requires a valid arif_init session. Outputs: organ dispatch envelope with recommended organ and tool.

NameTypeReqDescription
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
arguments––Arguments to pass to organ_tool.
contract_c_kwargs––Extra keyword arguments passed through to the organ tool call, as a JSON object.
intent––Natural-language description of what the user wants. e.g. "interpret this seismic section", "assess portfolio risk"
mission_id––Explicit human-cockpit mission binding (investigate|interpret| decide|build|monitor|remember). When set, skips keyword classification and binds the six-mission plan. Preferred…
mode––'route' (default) — classify intent and recommend the target organ; 'triage' — rank a batch of intents; 'delegate' — prepare an A2A handoff; 'status' — surface organ state; 'kernel' — kernel-level st…
organ––Optional explicit organ override. If provided, intent matching is skipped and this organ is used directly.
organ_tool––The tool name on the target organ to call. If absent, returns routing decision only (no bridge call).
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
task––Alias for intent (backward compat).
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_seal ~643

Appends a receipt to the VAULT999 immutable ledger. This is NOT a verdict and does not authorize anything — verdicts come only from arif_judge. Modes: seal (default; permanent append, requires payload and seal_purpose), verify (check one entry), ledger (read the ledger head), changelog (recent appends), audit (integrity check), session_close (close out a session into the ledger). Write modes require ack_irreversible=true. Outputs: immutable ledger entry receipt.

NameTypeReqDescription
ack_irreversibleboolean–Set true to confirm you understand sealed entries are PERMANENT — they can never be edited or removed.
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
actor_signature––Cryptographic signature over the request, if your agent holds a key — proves the call genuinely came from actor_id. Omit if you have no key.
constitutional––JSON block of governance metadata (floors consulted, chain references) — normally built by the kernel, not by callers.
constitutional_chain_id––Id of the evidence chain this call belongs to (observe→think→judge→seal). Copy it from the earlier step's response to link the steps together.
drift_events––JSON list of deviations observed, e.g. [{"what": "schema drift", "where": "tools/list"}] — stored with the record.
judge_state_hash––Hash string from the arif_judge SEAL response — ties this entry to the verdict that authorized it.
modestring–'seal' (default) — append a permanent entry; 'verify' — check one entry; 'ledger' — read the ledger head; 'changelog' — recent appends; 'audit' — integrity check; 'session_close' — close out a sessio…
nonce––One-time random string (e.g. a UUID) making this request unique; protects against replay of the same call.
payloadstring–The content to store forever, as a string (usually JSON-serialized) — the outcome, lesson, or record itself. Required for the write modes (seal, session_close); pure reads (verify, ledger, changelog,…
seal_purpose––One sentence saying why this verdict/record must exist, e.g. 'closing deployment D-17'. Stored permanently alongside the record.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
witness_typestring–Who witnessed the sealed fact: 'ai', 'human', or 'external' system.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

arif_think ~631

Structured reasoning and plan formulation — decomposes a question or claim into labeled derivations (OBS/DER/INT) before you act. Modes: reason (inquiry breakdown, default), reflect (self-review of prior reasoning), verify (check a derivation), axioms (surface hidden assumptions), plan/plan_review/plan_approve/refactor_plan (execution-plan lifecycle), metabolize (consolidate past reasoning), simulate (what-if), wonder (open exploration), atlas (map the problem space). Use to prepare evidence chains and plans BEFORE arif_judge or arif_forge — pass the returned plan_id to arif_forge when executing an approved plan. NOT for gathering facts (arif_observe), dispatching to organs (arif_route), or issuing verdicts (arif_judge — think never issues them). Pure reasoning: mutates no state and calls no external systems; its output is a reasoning record, not ground truth. Requires a valid arif_init session. Outputs: structured reasoning record with epistemic labels.

NameTypeReqDescription
actor_id––Your agent identity, e.g. 'kimi-code/FI-008' or 'claude/sonnet'. Recorded in the audit log so this action is attributed to you.
context––Structured sideband for the reasoning call — JSON object, e.g. {'handoff': <hermes_handoff_package envelope>}. Handoff context is reported as transport status only (REFS_RESOLVED / EVIDENCE_NOT_RECEI…
evidence––Prior verified facts to reason from — JSON list like [{'fact': 'tests pass', 'source': 'CI'}]; the derivation labels which evidence each conclusion rests on.
modestring–'reason' (default) — decompose a question; 'reflect' — self-review of prior reasoning; 'verify' — check a derivation; 'axioms' — surface hidden assumptions; 'plan'/'plan_review'/'plan_approve'/'refac…
plan_id––Plan reference from an earlier plan-mode response — needed for the review/approve/refactor steps.
query––The question, claim, or problem to reason about, in plain language.
session_id––Session id returned by arif_init (looks like 'sess-…'). Pass it on every call after init so the action is attributed to your governed session.
session_token––Session Continuity Token (SCT) — the credential string arif_init returned alongside session_id. Pass it back on follow-up calls to prove the session is yours; without it the kernel treats you as unau…
witness_typestring–Who vouches for the reasoning record: 'ai' (default), 'human', or 'external' system.
NameTypeReqDescription
actor_id–––
delta_S–––
metaobjectyes–
nine_signalobjectyes–
output_policystring––
philosophical_anchorobject––
reasonsarrayyes–
resultobjectyes–
session_id–––
stage_progression–––
statusstringyes–
timestampstringyes–
tool–yes–

No examples provided.

Install

How do I install the arifOS — Constitutional AI Governance MCP server?

arifOS — Constitutional AI Governance is a hosted endpoint at https://arifosmcp.arif-fazil.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · arifosmcp.arif-fazil.com

# add to Claude Code
claude mcp add --transport http ariffazil-arifosmcp 'https://arifosmcp.arif-fazil.com/mcp'
Common questions

What is the arifOS — Constitutional AI Governance MCP server?

arifOS — Constitutional AI Governance is an MCP server listed in the public MCP registry as io.github.ariffazil/arifosmcp. Constitutional AI governance: 11 mega-tools, 13 floors, VAULT999 ledger. Human-in-loop by design. This page covers its hosted endpoint (https://arifosmcp.arif-fazil.com/mcp).

Is the arifOS — Constitutional AI Governance MCP server safe to use?

arifOS — Constitutional AI Governance scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the arifOS — Constitutional AI Governance MCP server expose?

arifOS — Constitutional AI Governance exposes 9 tools: arif_init, arif_observe, arif_think, arif_route, arif_memory, and 4 more. Their descriptions and schemas cost roughly 6,832 tokens of context every time the server is loaded.

Does the arifOS — Constitutional AI Governance MCP server require authentication?

No. We connected to arifOS — Constitutional AI Governance without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the arifOS — Constitutional AI Governance MCP server still maintained?

arifOS — Constitutional AI Governance is marked deprecated in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.