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.

Decision Log

REMOTE · WWW.DECISIONLOG.AI

Append-only decisions with provenance, supersession, retrieval, and audited MCP actions.

0 this week 95 Trust /100

Last scanned (22 hours ago)

Scores higher than 99% of remote servers

Reachable. Last reached 4 Nov 2026.

Category Memory and Knowledge

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 Security97
Transport & Reachability100
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2101 tokens (~63/item across 33 items; 30 tools + 3 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 65% of tool parameters carry a description.Partial
  • 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 30 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.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.

  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 0
    • Stability: 0.97 → pass security
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 24 Aug 26 0
    • Transport: unverified → pass ▲ security
    • Authorization: Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. security
    • MCP protocol: unverified → pass ▲ functional
    • Schema quality: unverified → 100 ▲ functional
    • Tool coverage: unverified → 100 ▲ functional
    • First check of Schema quality: fail functional
    • First check of Tool coverage: 65 functional
    • First check of Capabilities: pass functional
    • First check of Schema quality: pass functional
    • First check of Schema quality: good functional
    • First check of Tool coverage: 100 functional
  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 31 Jul 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
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 4 Nov 2026 · Probed https://www.decisionlog.ai/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.decisionlog.ai CN=YR1,O=Let's Encrypt,C=US 15 Sept 2026 14 Dec 2026 RSA 2048 SHA256-RSA 5417eec6498875e2bfe81c709f446452548
SANs: *.decisionlog.ai, decisionlog.ai
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of www.decisionlog.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 1814, 3799 8, 8 Verified
decisionlog.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://www.decisionlog.ai/.well-known/oauth-protected-resource/api/mcp", scope="decision_log.api"

Bearer resource_metadata="https://www.decisionlog.ai/.well-known/oauth-protected-resource/api/mcp", scope="decision_log.api"
Header Value
strict-transport-security max-age=63072000

Protected resource metadata

Document https://www.decisionlog.ai/.well-known/oauth-protected-resource/api/mcp
Retrieved Yes
Resource https://www.decisionlog.ai/api/mcp
Authorisation server https://www.decisionlog.ai/api/auth

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://www.decisionlog.ai/api/mcp Verified 200
http (plaintext) http://www.decisionlog.ai/api/mcp HTTPS enforced 308 https://www.decisionlog.ai/api/mcp
MCP tools · 30 exposed · ~1,994 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
decision_log_approve_decision_action ~63

Record one immutable approval or rejection attestation.

NameTypeReqDescription
approvalGroupIdstringyesApproval group identifier.
approvalRequestIdstringyesApproval request identifier.
commentstring–Optional approval comment.
decisionstringyes–
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_convert_candidate_to_supersession ~77

Approve a pending DecisionCandidate as the immutable replacement for one current Decision, preserving provenance and supersession history.

NameTypeReqDescription
candidateIdstringyesPending DecisionCandidate identifier.
reasonstring–Optional reason for the supersession.
replacesDecisionIdstringyesCurrent Decision identifier that the candidate replaces.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_create_candidate ~101

Create a reviewable DecisionCandidate.

NameTypeReqDescription
confidenceinteger––
decisionTextstringyesThe immutable meaning of the decision.
decisionTypestringyes–
metadataobject––
rationalestringyesWhy the decision was made.
sourceIdsarray––
summarystring–Optional summary.
titlestringyesConcise direct-action title without speaker wrappers or ellipses.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_create_decision ~103

Create an immutable Decision when permitted, otherwise create a reviewable DecisionCandidate.

NameTypeReqDescription
decisionTextstringyesThe immutable meaning of the decision.
decisionTypestringyes–
metadataobject––
rationalestringyesWhy the decision was made.
sourceIdsarray––
summarystring–Optional summary.
titlestringyesConcise direct-action title without speaker wrappers or ellipses.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_get_candidate ~40

Get the complete visible review context for one DecisionCandidate before approving, rejecting, or converting it.

NameTypeReqDescription
candidateIdstringyesDecisionCandidate identifier.
NameTypeReqDescription
resultobjectyesThe complete visible DecisionCandidate review model, including classification, alternatives, criteria, and source identifiers.

No examples provided.

decision_log_get_current_decision ~30

Get the newest active decision in a domain.

NameTypeReqDescription
domainstringyesDomain slug.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_get_decision ~27

Retrieve one decision by ID.

NameTypeReqDescription
decisionIdstringyesDecision identifier.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_get_decision_governance ~37

Retrieve lock, authority snapshot, and approval state for a Decision.

NameTypeReqDescription
decisionIdstringyesDecision identifier.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_get_decision_sources ~43

Retrieve retention-safe provenance links for one visible Decision, including relationship, source lifecycle, and submitter metadata.

NameTypeReqDescription
decisionIdstringyesDecision identifier.
NameTypeReqDescription
resultarrayyes–

No examples provided.

decision_log_get_source ~52

Retrieve one visible SourceContent detail projection. Redacted, purged, and unknown retention states never return stored title, content, blob URL, or metadata.

NameTypeReqDescription
sourceIdstringyesSourceContent identifier.
NameTypeReqDescription
resultobjectyes–

No examples provided.

decision_log_get_source_decisions ~49

Retrieve visible DecisionSource links for one SourceContent record with each linked Decision's lifecycle, authoritative current-state, and supersession identity.

NameTypeReqDescription
sourceIdstringyesSourceContent identifier.
NameTypeReqDescription
resultarrayyesVisible DecisionSource links for one SourceContent record, paired with the minimal Decision lifecycle projection.

No examples provided.

decision_log_get_supersession_history ~56

Retrieve the complete visible Decision supersession chain in oldest-to-newest order. Malformed chains fail closed and never claim a current Decision.

NameTypeReqDescription
decisionIdstringyesDecision identifier from any point in the chain.
NameTypeReqDescription
resultobjectyes–

No examples provided.

decision_log_list_audit_events ~107

List the visible append-only audit events for the current Organization using the canonical permission-aware, attribution-safe projection.

NameTypeReqDescription
actionstring–Optional exact AuditEvent action.
actorTypestring–Optional exact actor type.
limitinteger––
offsetinteger––
querystring–Optional actor, action, resource, or identifier search.
resourceTypestring–Optional exact resource type.
sortstring––
NameTypeReqDescription
resultarrayyes–

No examples provided.

decision_log_list_candidates ~91

List reviewable DecisionCandidates visible in the current Organization and Workspace before taking a resolution action.

NameTypeReqDescription
decisionTypestring–Optional exact decision type.
limitinteger––
offsetinteger––
querystring–Optional title, summary, decision text, or rationale search.
sortstring––
statusstring–Optional exact candidate review status.
NameTypeReqDescription
resultarrayyesVisible DecisionCandidates in the current Organization and Workspace.

No examples provided.

decision_log_list_decisions_by_domain ~31

List decisions related to an exact domain slug.

NameTypeReqDescription
domainstringyesDomain slug.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_list_decisions_by_tag ~31

List decisions related to an exact tag slug.

NameTypeReqDescription
tagstringyesTag slug.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_list_recent_decisions ~29

List the most recent decisions in the authenticated workspace.

NameTypeReqDescription
limitinteger––
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_list_sources ~85

List visible SourceContent using bounded excerpts and canonical retention redaction.

NameTypeReqDescription
limitinteger––
offsetinteger––
querystring–Optional title, content, or external identifier search.
retentionStatestring–Optional exact retention lifecycle state.
sortstring––
sourceTypestring–Optional exact source type.
NameTypeReqDescription
resultarrayyesVisible SourceContent summaries with bounded excerpts and retention redaction applied.

No examples provided.

decision_log_lock_decision ~63

Irreversibly prevent a current Decision from ever being superseded; may create an approval request.

NameTypeReqDescription
decisionIdstringyesDecision to lock.
rationalestringyesWhy permanent finality is required.
sourceIdsarray––
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_render_audit_explorer ~51

Use this when the user wants to visually inspect attributable, append-only audit events with filtering and pagination.

NameTypeReqDescription
limitinteger––
querystring–Optional audit event filter.
NameTypeReqDescription
actors–––
events–yes–
surfacestringyesWorkflow surface.

No examples provided.

decision_log_render_candidate_review ~43

Use this when the user wants to inspect and disposition one known DecisionCandidate in a visual review workbench.

NameTypeReqDescription
candidateIdstringyesDecisionCandidate identifier.
NameTypeReqDescription
actors–––
candidate–yes–
surfacestringyesWorkflow surface.

No examples provided.

decision_log_render_decision ~55

Use this when the user wants to inspect one known Decision in a visual card. Call a data retrieval tool first when the Decision ID is unknown.

NameTypeReqDescription
decisionIdstringyesDecision identifier returned by a retrieval tool.
NameTypeReqDescription
decision–yes–

No examples provided.

decision_log_render_decision_explorer ~47

Use this when the user wants to browse the five most recent Decisions and optionally inspect one in detail.

NameTypeReqDescription
decisionIdstring–Optional Decision identifier to open immediately.
NameTypeReqDescription
actors–––
decisions–yes–
selected–––
surfacestringyesWorkflow surface.

No examples provided.

decision_log_render_source_pipeline ~42

Use this when the user wants to inspect one known source, its provenance lifecycle, and extracted candidates.

NameTypeReqDescription
sourceIdstringyesDecisionSource identifier.
NameTypeReqDescription
actors–––
candidates–yes–
source–yes–
surfacestringyesWorkflow surface.

No examples provided.

decision_log_render_supersession_composer ~134

Use this when the user has a known active Decision and complete replacement meaning to review before supersession.

NameTypeReqDescription
decisionIdstringyesDecision being superseded.
decisionTextstringyesThe immutable meaning of the decision.
decisionTypestringyes–
metadataobject––
rationalestringyesWhy the decision was made.
reasonstringyesReason for supersession.
sourceIdsarray––
summarystring–Optional summary.
titlestringyesConcise direct-action title without speaker wrappers or ellipses.
NameTypeReqDescription
actors–––
current–yes–
reasonstringyesReason for supersession.
replacement–yes–
surfacestringyesWorkflow surface.

No examples provided.

decision_log_render_workspace_brief ~32

Use this when the user wants a visual briefing of recent decisions, pending candidates, and source activity.

Input schema present but exposes no named parameters.

NameTypeReqDescription
actors–––
candidates–yes–
decisions–yes–
sources–yes–
surfacestringyesWorkflow surface.

No examples provided.

decision_log_resolve_candidate ~124

Approve or reject a pending DecisionCandidate.

NameTypeReqDescription
candidateIdstringyesCandidate identifier.
decisionTextstring–The immutable meaning of the decision.
decisionTypestring––
metadataobject––
rationalestring–Why the decision was made.
reasonstring–Optional rejection reason.
resolutionstringyes–
sourceIdsarray––
summarystring–Optional summary.
titlestring–Concise direct-action title without speaker wrappers or ellipses.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_search_decisions ~134

Search decisions in the authenticated workspace.

NameTypeReqDescription
currentOnlyboolean––
decisionKeystring–Optional stable Decision key filter.
decisionTypestring–Optional Decision type filter.
domainstring–Optional Domain slug filter.
includeSupersededboolean––
limitinteger––
offsetinteger––
projectId––Optional Project identifier filter.
querystring–Search text.
sortstring––
statusstring–Optional Decision status filter.
tagstring–Optional Tag slug filter.
NameTypeReqDescription
resultobjectyes–

No examples provided.

decision_log_submit_source ~91

Submit source content for ingestion and later provenance links.

NameTypeReqDescription
contentBlobUrlstring––
contentTextstring–Inline source text.
externalIdstring–External provider identifier.
externalUrlstring––
metadataobject––
sourceTypestring–Source type; defaults to mcp.
titlestring–Optional source title.
NameTypeReqDescription
result–yes–

No examples provided.

decision_log_supersede_decision ~126

Create a replacement Decision and supersession relationship for an existing Decision.

NameTypeReqDescription
decisionIdstringyesDecision being superseded.
decisionTextstringyesThe immutable meaning of the decision.
decisionTypestringyes–
metadataobject––
rationalestringyesWhy the decision was made.
reasonstringyesReason for supersession.
sourceIdsarray––
summarystring–Optional summary.
titlestringyesConcise direct-action title without speaker wrappers or ellipses.
NameTypeReqDescription
result–yes–

No examples provided.

Install

How do I install the Decision Log MCP server?

Decision Log is a hosted endpoint at https://www.decisionlog.ai/api/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 · www.decisionlog.ai

# add to Claude Code
claude mcp add --transport http ai-decisionlog-mcp 'https://www.decisionlog.ai/api/mcp'
Common questions

What is the Decision Log MCP server?

Decision Log is an MCP server listed in the public MCP registry as ai.decisionlog/mcp. Append-only decisions with provenance, supersession, retrieval, and audited MCP actions. This page covers its hosted endpoint (https://www.decisionlog.ai/api/mcp).

Is the Decision Log MCP server safe to use?

Decision Log scores 95 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 Decision Log MCP server expose?

Decision Log exposes 30 tools: decision_log_create_decision, decision_log_search_decisions, decision_log_get_decision, decision_log_supersede_decision, decision_log_lock_decision, and 25 more. Their descriptions and schemas cost roughly 1,994 tokens of context every time the server is loaded.

Does the Decision Log MCP server require authentication?

Yes. Decision Log asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Decision Log MCP server still maintained?

Decision Log is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.