
Decision Log MCP server
Which MCP servers are Decision Log's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry nameai.decisionlog/mcpverified in the MCP registry
The registry name sits under decisionlog.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools30
- Server calls itselfdecision-log
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 134 ms.
- Its tools do every use case we checked: Find the active decision and its replacement history; Trace the rationale and sources behind an earlier choice.
Once connected
- For "Find the active decision and its replacement history", the likely first call is decision_log_get_current_decision.
- For "Trace the rationale and sources behind an earlier choice", the likely first call is decision_log_search_decisions.
- Parameters are untyped or undescribed in 14 of 30 tools: check arguments before calling.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score97 of 100answers 100 · does the job 100 · definitions 92 · context 91 · connects 100
- What an agent can do with it2 of 2 use cases
- Answered100% of days14 of 14 daily checks
- Median first answer807 ms
- Space in an agent's context≈ 4,121 tokensthe definitions of all its tools (30), which an agent carries on every turn
- Tool definitionsA · 92 of 100
- Typed results30 of 30 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 14 of 30
What an agent can do with it
- can do · Find the active decision and its replacement history
- can do · Trace the rationale and sources behind an earlier choice
- not sure · Review agent-proposed decisions before they take effect
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
decision_log_create_decisionCreate an immutable Decision when permitted, otherwise create a reviewable DecisionCandidate.
decision_log_search_decisionsSearch decisions in the authenticated workspace.
decision_log_get_decisionRetrieve one decision by ID.
decision_log_supersede_decisionCreate a replacement Decision and supersession relationship for an existing Decision.
decision_log_lock_decisionIrreversibly prevent a current Decision from ever being superseded; may create an approval request.
decision_log_approve_decision_actionRecord one immutable approval or rejection attestation.
decision_log_get_decision_governanceRetrieve lock, authority snapshot, and approval state for a Decision.
decision_log_list_recent_decisionsList the most recent decisions in the authenticated workspace.
decision_log_submit_sourceSubmit source content for ingestion and later provenance links.
decision_log_list_sourcesList visible SourceContent using bounded excerpts and canonical retention redaction.
decision_log_get_sourceRetrieve one visible SourceContent detail projection. Redacted, purged, and unknown retention states never return stored title, content, blob URL, or metadata.
decision_log_get_source_decisionsRetrieve visible DecisionSource links for one SourceContent record with each linked Decision's lifecycle, authoritative current-state, and supersession identity.
decision_log_list_candidatesList reviewable DecisionCandidates visible in the current Organization and Workspace before taking a resolution action.
decision_log_get_candidateGet the complete visible review context for one DecisionCandidate before approving, rejecting, or converting it.
decision_log_create_candidateCreate a reviewable DecisionCandidate.
decision_log_resolve_candidateApprove or reject a pending DecisionCandidate.
decision_log_convert_candidate_to_supersessionApprove a pending DecisionCandidate as the immutable replacement for one current Decision, preserving provenance and supersession history.
decision_log_get_current_decisionGet the newest active decision in a domain.
decision_log_get_supersession_historyRetrieve the complete visible Decision supersession chain in oldest-to-newest order. Malformed chains fail closed and never claim a current Decision.
decision_log_get_decision_sourcesRetrieve retention-safe provenance links for one visible Decision, including relationship, source lifecycle, and submitter metadata.
decision_log_list_audit_eventsList the visible append-only audit events for the current Organization using the canonical permission-aware, attribution-safe projection.
decision_log_list_decisions_by_tagList decisions related to an exact tag slug.
decision_log_list_decisions_by_domainList decisions related to an exact domain slug.
decision_log_render_decisionUse 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.
decision_log_render_workspace_briefUse this when the user wants a visual briefing of recent decisions, pending candidates, and source activity.
decision_log_render_decision_explorerUse this when the user wants to browse the five most recent Decisions and optionally inspect one in detail.
decision_log_render_candidate_reviewUse this when the user wants to inspect and disposition one known DecisionCandidate in a visual review workbench.
decision_log_render_supersession_composerUse this when the user has a known active Decision and complete replacement meaning to review before supersession.
decision_log_render_source_pipelineUse this when the user wants to inspect one known source, its provenance lifecycle, and extracted candidates.
decision_log_render_audit_explorerUse this when the user wants to visually inspect attributable, append-only audit events with filtering and pagination.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"decisionlog": {
"type": "http",
"url": "https://www.decisionlog.ai/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http decisionlog https://www.decisionlog.ai/api/mcpclaude.ai, ChatGPT and other clients: add https://www.decisionlog.ai/api/mcp as a custom connector in the settings.
OpenAPI spec
89 paths, read 2026-10-21. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.