Agile Today
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Project management methodology graph: route planning, stage-gate decisions and plan checks.
| Author | org.agile-today |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2645 ms |
| Last measured | 2026-10-26 |
Measured statistics
| Tools measured | 8 |
|---|---|
| Latency, 30-day median (L1) | 2645 ms |
| Latency, latest (L1) | 2645 ms |
| Safe-call success | 1/1 (100%) |
| 30-day success rate (L2) | 100% |
| Last checked | 2026-10-26 |
| Total checks | 4 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Agile Today": {
"url": "https://agile-today.org/api/mcp?src=mcp-registry",
"transport": "streamable-http"
}
}
}
Measured tools (8)
list_contextread-onlyCall first. Returns the context dimensions and flags (with defaults and how many rules each flag drives), stages, gates, evidence states and levels, the gate outcome precedence and the suggested workflow.
Parameters:
lang— string — Answer language, default en
Hints: read-only yes · destructive no · idempotent yes · open-world no
plan_projectread-onlyRoute from presale to closure for a project context. Default is compact (ids by strength + a names dictionary, core items and gate evidence for all stages, about 6–10k characters). Ask for one stage with stages:['st.design'] and format:'full' for reasons, avoid texts and gate details. 'core' = do it here (context rule, flag or gate-critical artifact), at most 8 work items per stage (producers of the gate's critical artifacts first, then context rules, then flags).
Parameters:
lang— string — Answer language, default enformat— string — Default compactstages— array — Stage ids or codes, e.g. ['st.analysis','design']. Default: allcontext— object — Project context. Unknown keys and values are rejected in the answer envelope with did_you_mean. Defaults: software, hybrid, complicated, tm, single, medium size, ui, data.include— array — Default all fourmin_strength— string — Default: core for all stages, all when stages are given
Hints: read-only yes · destructive no · idempotent yes · open-world no
check_gateread-onlyEvaluates gate g.g0 … g.g10 against your evidence. Outcome precedence: Stop > Recycle > Hold > Conditional go > Go, with the rule that fired (outcome_reason). Critical evidence missing or stale → Hold; required non-critical missing, or a waiver without a reason or an approver who decides at this gate → Conditional go; a waiver with both → Go with the Waiver modifier (under regulation a waived critical artifact stays Conditional go until the deviation is recorded with the quality approval); optional gaps are notes. Modifiers: Work started without the gate, Overdue, Stale, Waiver. gate.deciders decide, gate.advisors take part. A disproved key product hypothesis is a Recycle, not a Stop: pass earlier_stage_invalid:true with invalid_stage:'st.discovery'. At G8 (go / no-go), work_started_beyond:true means production was changed before the decision: Hold (R3), not a Go with a modifier. Call without evidence to list what the gate needs. Returns a receipt hash of the inputs.
Parameters:
gate(required) — string — Gate id, e.g. g.g5lang— string — Answer language, default encontext— object — Project context. Unknown keys and values are rejected in the answer envelope with did_you_mean. Defaults: software, hybrid, complicated, tm, single, medium size, ui, data.evidence— object — Map artifact id → state or {state, reason, ref, by, date}. A waiver is {state:'waived', reason, by}: by is the role id of a decider of this gate (see gate.deciders, e.g. r.client_owner) or 'name, role'. Unknown ids are reported as warnings with a suggestion.grace_days— number — Overrides both limits. Default: 80% of planned_stage_days, else by approach (predictive/hybrid 10, agile/flow 5); required evidence then waits twice as longdays_in_stage— numberinvalid_stage— string — With earlier_stage_invalid: the stage to return to, if knowninvalid_artifact— string — With earlier_stage_invalid: the artifact that is no longer true, to find where to returnplanned_stage_days— number — Planned length of the stage in days. With it, missing critical evidence is overdue after 80% of it and missing required evidence after all of itbusiness_case_valid— boolean — false → Stopwork_started_beyond— boolean — True if work of later stages already started (adds the 'work started without the gate' modifier; at G8 it is a Hold)earlier_stage_invalid— boolean — true → Recycle; the answer names the stage to return to
Hints: read-only yes · destructive no · idempotent yes · open-world no
when_to_useread-onlyFor one event, practice, technique, notation, tool, artifact or antipattern: does it fit this context (fits / avoid / not_applicable / antipattern), its strength and why, alternatives and their group advice, risks, and which gates require it.
Parameters:
id(required) — string — e.g. t.planning_poker, p.stage_gating, x.velocity_kpilang— string — Answer language, default encontext— object — Project context. Unknown keys and values are rejected in the answer envelope with did_you_mean. Defaults: software, hybrid, complicated, tm, single, medium size, ui, data.
Hints: read-only yes · destructive no · idempotent yes · open-world no
check_mixread-onlyFor a set of ids: antipatterns in the set and detected by rules, conflicts, redundant alternatives (e.g. seven estimation methods), items to avoid or not applicable here, risks, missing inputs and suggested additions. ok = no antipatterns, conflicts, avoid or not-applicable items; a detected pattern of severity warning (e.g. output over outcome on a client contract) does not change ok.
Parameters:
ids(required) — arraylang— string — Answer language, default encontext— object — Project context. Unknown keys and values are rejected in the answer envelope with did_you_mean. Defaults: software, hybrid, complicated, tm, single, medium size, ui, data.
Hints: read-only yes · destructive no · idempotent yes · open-world no
validate_planread-onlyChecks an ordered list of steps (stages, gates, events, practices, techniques, notations, artifacts). Errors: empty plan, unknown ids, non-step types, stage order (analysis and design work planned early is only a warning 'early'; building before G3–G5 is an order error), contract after delivery gates, a gate after the step it authorises (G8 after the cutover), antipatterns, avoid or not-applicable items. Warnings: duplicates, redundant alternatives, early work, a cutover with no G8 or go / no-go meeting before it, antipatterns of severity warning. 'Shadow start' looks at the order: G4 or G5 must come before the first build step. 'expected' lists gate evidence not yet produced by earlier steps.
Parameters:
steps(required) — arraylang— string — Answer language, default encontext— object — Project context. Unknown keys and values are rejected in the answer envelope with did_you_mean. Defaults: software, hybrid, complicated, tm, single, medium size, ui, data.evidence— object — Artifacts that already exist
Hints: read-only yes · destructive no · idempotent yes · open-world no
search_graphread-onlySearch names, ids, descriptions and aliases in English and Russian (word stems, small typos tolerated). Returns total and the best matches.
Parameters:
query(required) — stringlang— string — Answer language, default entype— stringlimit— integer
Hints: read-only yes · destructive no · idempotent yes · open-world no
explain_noderead-onlyOne node with its description, conditions, source, level and its links grouped by type, each with a link id (Lxxxx) to cite. Filter with link_types, direction and limit.
Parameters:
id(required) — stringlang— string — Answer language, default enlimit— integerdirection— stringlink_types— array
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.