principia
Server Details
Source-graded registry of organizational measurement: constructs, priors, instruments, citations.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 27.3% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 36 tools
Several entity families collide: `models.*` ("theoretical / structural frameworks") vs `theoretical_models.*` ("canonical theoretical models") are nearly indistinguishable, `canonical_priors.*` vs `priors.moderators` both address synthesized priors, and `canonical_items.*` vs `items.*` both concern survey items at different granularities. Descriptions do differentiate constructs/measures and evidence.for/trace, but an agent can easily pick the wrong namespace for models, priors, and items.
Names are uniformly dot-namespaced lowercase (`<namespace>.<verb>`), with list/lookup/search repeated across most families. A few tools break the verb-final pattern (`constructs.measures`, `evidence.for`, `priors.moderators`), which is a minor deviation rather than an inconsistency.
36 tools exceeds a comfortable surface and is inflated by duplicate-looking families (models vs theoretical_models, canonical_items vs items, canonical_priors vs priors) plus several single-tool namespaces (effects.search, evidence_statements.search, priors.moderators). The underlying domain is large, but consolidation into fewer entity-neutral tools would reduce the count substantially.
The surface is deliberately read-only (curator-policy D4), so missing writes are by design and core entities have lookup+search. But coverage is uneven: no list for citations, critiques, equivalences, interventions, items, or canonical_priors; `effects` has only search with no id lookup; `measures` has list/lookup but no search; and priors are reachable only via lookup/search/moderators.
Available Tools
36 toolsprincipia.canonical_items.listARead-onlyInspect
List CanonicalSurveyItem rows (PRN-050 item-level dedup spine). Each row aggregates one normalized item stem across N source instruments via source_items[].
Inputs: limit, offset. Returns: total, canonical_items
principia.canonical_items.lookupARead-onlyInspect
Lookup one CanonicalSurveyItem by canonical_item_id (e.g., CITM_7350938cb42d). Unknown ids return found:false.
Inputs: id (required). Returns: found, canonical_item
principia.canonical_items.searchARead-onlyInspect
Keyword search over normalized_text + alternative_texts. Optional instrument_id filter narrows to canonical items whose source_items[] reference that instrument.
Inputs: q (required), limit, instrument_id. Returns: matches
principia.canonical_priors.lookupBRead-onlyInspect
Lookup a synthesized Bayesian prior by id OR (from_construct_id, predicate, to_construct_id). Empty until PRN-021 synthesis engine ships. PRN-N1013-M4: a prior's r pools observed and corrected contributing effects without a per-row marker yet (EFFECT_ESTIMATE_GLOSSARY.units_not_recorded, @people-analyst/measurement-core) — read it as basis-not-recorded, not as raw r.
Inputs: id, predicate, sample_culture, to_construct_id, +1 more. Returns: note, found, prior, reason, +2 more
principia.canonical_priors.searchARead-onlyInspect
Search canonical priors by from/predicate/to. Empty until PRN-021 synthesis engine ships.
Inputs: to, from, limit, predicate, +4 more. Returns: note, total, matches, resolved_construct_ids
principia.citations.lookupARead-onlyInspect
Lookup one citation by id OR doi. Scans both id-keyed and doi-keyed candidates.
Inputs: id, doi. Returns: found, citation
principia.citations.searchBRead-onlyInspect
Keyword search over title + apa_reference + doi + authors.
Inputs: q (required), limit. Returns: matches
principia.constructs.listARead-onlyInspect
List canonical constructs (resolved CanonicalVariable rows). Supports limit/offset, engagement_family_only, and abstraction_level (PRN-271).
Inputs: limit, offset, abstraction_level, engagement_family_only. Returns: total, constructs
principia.constructs.lookupARead-onlyInspect
Lookup one canonical construct by id (a canonical variable_id, e.g. VAR_000376). Unknown ids return found:false (soft validation).
Inputs: id (required). Returns: found, construct
principia.constructs.measuresBRead-onlyInspect
Return instruments that measure a given construct, ranked by composite score (reliability + validity + literature usage + recency). Optional filters: min_reliability, cross_cultural_only, length_lte. Read-only — no mutation (curator-policy D4).
Inputs: construct_id (required), limit, length_lte, min_reliability, +1 more. Returns: items, total, construct_id, generated_at
principia.constructs.resolveARead-onlyInspect
Resolve a source-side construct {name, definition?, variable_code?} against the canonical store. READ-ONLY — does not mutate. Uses meta-factory's matcher (name@0.9 / code@0.85 / definition@0.6).
Inputs: name (required), definition, variable_code. Returns: kind, construct, confidence, match_type
principia.constructs.searchARead-onlyInspect
Keyword search over construct name + definition + alternative_names + variable_codes. Argument is q (not query).
Inputs: q (required), limit. Returns: matches
principia.critiques.lookupARead-onlyInspect
Look up one MethodologyCritique by critique_id. Returns {matches, total, note?} — array-shaped for parity with equivalences. Matches list contains 0 or 1 element.
Inputs: id (required). Returns: note, total, matches
principia.critiques.searchARead-onlyInspect
Search MethodologyCritique rows by composite filter (subject_id, subject_type, critique_type, severity). All filters AND together; any subset of the four is valid. Read-only (curator-policy D4).
Inputs: limit, severity, subject_id, subject_type, +1 more. Returns: note, total, matches
principia.effects.searchCRead-onlyInspect
Search EffectSize rows by from/to/statistic_type. Each returned value's observed/corrected basis is named per EFFECT_ESTIMATE_GLOSSARY (@people-analyst/measurement-core) — PRN-N1013-M4; a row with no typed estimates block reads 'basis not recorded', never a bare statistic symbol.
Inputs: to, from, limit, statistic_type, +2 more. Returns: note, matches
principia.equivalences.lookupARead-onlyInspect
Look up InstrumentEquivalence rows by id OR by the canonical tuple (construct_id + instrument_a + instrument_b [+ optional mapping_method]). Pair ordering is normalized server-side so (Q12, UWES-9) and (UWES-9, Q12) resolve to the same row. Returns {matches, total, note?} — array-shaped because a (construct, pair) can carry multiple methods.
Inputs: id, construct_id, instrument_a, instrument_b, +1 more. Returns: note, total, matches
principia.equivalences.searchARead-onlyInspect
Search InstrumentEquivalence rows by construct_id and/or instrument_id. instrument_id matches either side of the pair. Optional mapping_method filter.
Inputs: limit, construct_id, instrument_id, mapping_method. Returns: note, total, matches
principia.evidence.forBRead-onlyInspect
Return Evidence[] edges that name a given entity_id as the claim subject.
Inputs: entity_id (required), limit, subject_type. Returns: note, evidence
principia.evidence_statements.searchBRead-onlyInspect
Search owned, OA-sourced, attributed, stance-classified evidence quotes for a construct→construct relationship (from/to), or any statement naming a single construct. Filters: stance, displayable_only. The display layer for the metric profile page + book.
Inputs: to, from, limit, stance, +3 more. Returns: note, total, statements
principia.evidence.traceARead-onlyInspect
Retrieve the full causal chain from a construct, condition, or problem to interventions, with evidence grades at each hop. problem_id accepts pf.* addresses from the problemframe-2026-v1 frozen registry (cert d0770859) and resolves construct mappings via the MF-711 pf→construct join (landed 2026-09-11); an address with no join coverage yet resolves the problem frame with an honestly empty linked_constructs[], not an error. condition_id accepts bicycle-guide's minted cond_ ConditionFrame ids and resolves via the PRN-281 crosswalk (landed 2026-09-11); a condition with no construct match yet resolves honestly empty the same way. All three entry points are fully resolved today — no path is gated.
Inputs: problem_id, condition_id, construct_id, limit_priors, +1 more. Returns: gate, d_range, problem, traced_at, +6 more
principia.instruments.listCRead-onlyInspect
List InstrumentCard rows. Optional construct_id filter narrows to instruments covering a given construct.
Inputs: limit, owned, offset, license, +1 more. Returns: total, instruments
principia.instruments.lookupARead-onlyInspect
Lookup one instrument by instrument_id. Unknown ids return found:false.
Inputs: id (required). Returns: found, instrument
principia.instruments.searchBRead-onlyInspect
Keyword search over instrument_name + developer + constructs_covered.
Inputs: q (required), limit. Returns: matches
principia.interventions.lookupARead-onlyInspect
Look up one Intervention by intervention_id, InterventionFrame frame_node_id (ifn_…) or frame address (<family>.<class>[.<practice>]). Returns {matches, total, note?} — array-shaped for parity with critiques + equivalences; 0 or 1 match. The match carries computed frame (node id, address, L1 family) and evidence blocks: declared target edges, each linked effect guarded by PRN-649 (unchecked value, CI, k, N and CI-derived claims omitted with numbers_withheld; checked values carry check labels), basis (machine_extracted | human_reviewed), thin flag and the verbatim source span or why none is held, plus an evidence_state (missing | thin | machine_extracted | human_reviewed) and measurement_tier. Neither block is stored on the row.
Inputs: id (required). Returns: note, total, matches
principia.interventions.searchARead-onlyInspect
Search Intervention rows by composite filter (construct_id — matches when targets_constructs[] includes the id; problem_id — a ProblemFrame pf.* address, resolved via the MF-711 pf→construct join to one or more construct ids and then matched the same way as construct_id; modality — matches when delivery_modality[] includes the modality; cost_band — exact match on typical_cost_band; family — an InterventionFrame L1 family slug). All filters AND together; any subset is valid. Each match carries a computed frame block. view: "families" adds families[] (every L1 family with its definition and the frame nodes under it) and unplaced[] (address exceptions). Read-only (curator-policy D4).
Inputs: view, limit, family, modality, +3 more. Returns: note, total, matches, families, +1 more
principia.items.lookupARead-onlyInspect
Lookup one survey item by item_id. SPEC §6/Q4 enforced: items_license != public_domain|open returns status:'restricted'.
Inputs: id (required). Returns: item, found, reason, status, +1 more
principia.items.searchARead-onlyInspect
Search items by text. Restricted items (proprietary instruments) are returned with text fields stripped; restricted_count surfaces how many.
Inputs: q (required), limit. Returns: matches, restricted_count
principia.measures.listBRead-onlyInspect
List Measure rows. entity_kind filter selects scientific_construct vs operational_metric.
Inputs: limit, offset, entity_kind. Returns: total, measures
principia.measures.lookupARead-onlyInspect
Lookup one Measure by measure_id. Unknown ids return found:false.
Inputs: id (required). Returns: found, measure
principia.models.listCRead-onlyInspect
List Model rows (theoretical / structural frameworks).
Inputs: limit, offset. Returns: total, models
principia.models.lookupARead-onlyInspect
Lookup one Model by model_id. Unknown ids return found:false.
Inputs: id (required). Returns: found, model
principia.models.searchBRead-onlyInspect
Keyword search over model_name + description.
Inputs: q (required), limit. Returns: matches
principia.priors.moderatorsBRead-onlyInspect
One canonical prior's moderator groups (moderated_by[], levels in level order, marginal level named) plus the served-prior content ETag. Same ETag the REST route /api/v1/priors/// sends. Unmoderated priors return an empty list; nothing is invented.
Inputs: id, predicate, to_construct_id, from_construct_id. Returns: etag, note, found, moderated, +2 more
principia.theoretical_models.listARead-onlyInspect
List canonical theoretical models (JD-R, COR, SDT, AET, JCM, Goal-Setting, Equity, Two-Factor, etc.). Sorted by foundational publication year. Read-only.
Inputs: limit, offset. Returns: items, total
principia.theoretical_models.lookupARead-onlyInspect
Look up one CanonicalTheoreticalModel by id (e.g., theory.jd_r). Returns the theory's canonical constructs, canonical relations (with predicates), descendant per-study models, and foundational citations.
Inputs: id (required). Returns: note, found, theoretical_model
principia.theoretical_models.searchARead-onlyInspect
Search theoretical models by keyword over name/summary/constructs. Optional filters: invokes_construct_id (theories that invoke a specific construct), field_domain (classification axis).
Inputs: q (required), limit, field_domain, invokes_construct_id. Returns: total, matches
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Variable relationships from research papers with causal direction and source traceback.
Researcher profiles, works, affiliations, funding, and peer reviews from the ORCID registry.
Scholarly literature search across nine sources
PRISMA 2020 systematic reviews as MCP tools - verified citations, IMRAD papers
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server for the Meta-Consciousness (MCAI) theory: term definitions, concept relations and source citations, served from a local knowledge base.27MIT
- AlicenseCqualityBmaintenanceAn append-only research operations framework and read-only MCP that tracks research plans, approvals, observations, claims, failures, revisions, and contributions with source-grounded evidence, providing search, evidence fetch, and audit capabilities without direct ledger writes.3091 PyPIMIT
- AlicenseNot gradedqualityDmaintenanceA stdio MCP server for traceable scholarly retrieval and evidence-grounded literature review, with deterministic provider fusion, conservative ID canonicalization, and provenance-preserving citation traversal.2MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables auditing scientific papers for methodological biases such as selection bias and p-hacking, and assessing citation credibility and research consensus.-
Glama MCP Gateway
Add one secure layer between your agents and this server.