Strata
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STRATA_DB | No | Path to the Strata Relate .rl store file the MCP server reads and writes. Optional; defaults to the bundled/copied Strata store if not set. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Strata holds archaeological excavations as a graph in one Relate file.
Model: (:Site)<-[:IN_SITE]-(:Trench)<-[:IN_TRENCH]-(:Context) — a Context is a stratigraphic unit (locus, layer, cut, fill, wall). (a)-[:ABOVE]->(b) means a is LATER than b (lies over it, cuts it, fills it, seals it); r.verbs says which and r.stated_by lists the unit records that state it. :CONTESTED is an ABOVE claim set aside because it contradicts another; :REJECTED is one an archaeologist ruled out. (:Find)-[:FROM {bag}]->(:Context); (:Context)-[:DATED_TO]->(:Period); (:Context)-[:IN_PHASE]->(:Phase); (:Issue)-[:INVOLVES]->(:Context) are check results; (:Edit)-[:TOUCHED]->(:Context) is the interpretive history. Context.depth is the unit's row in the Harris matrix (0 = top/latest).
Name units by full path, e.g. "Area D/Trench 6/Locus 20". store_info says which .rl file you are reading and writing; say so when the user asks where their data or edits are.
Rules:
Answer from the graph. Cite unit paths and, for claims, the records that state them.
Never invent a stratigraphic relation. Propose one only when the user or the record's own text supports it, and put that evidence in
note.resolve_order settles a dispute between excavators' records: ask the user to confirm before calling it, and quote the competing claims (explain_issue).
A refused edit is information, not an error: report the chain that refuses it.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| store_infoA | Which Relate file this server reads and writes (path, size, last change), why that file, the sites in it, and how many interpretive edits it holds. |
| overviewB | Every site in the store: contexts, relations, contested claims, finds, open issues. |
| queryA | Run a read-only Cypher query against the store (it is always rolled back).
Returns columns, rows (at most |
| describeC | One unit: its record, matrix depth, what lies directly above/below, same-as units, contested claims, finds and open issues. |
| belowC | Every unit stratigraphically earlier than |
| aboveC | Every unit stratigraphically later than |
| relationC | How two units relate: earlier, later, same, contested or unknown, with the chain of records that proves it and any contested direct claims. |
| date_bracketB | Terminus post quem and ante quem for a unit from the dated units below and above it, and whether its recorded date fits. Years are astronomical: -1899 is 1900 BCE. |
| provenanceC | Where a find came from and what dates it: find -> bag -> unit -> period -> site, the units sealing it, open caveats, and its date bracket. |
| issuesB | Open problems found by the checks, most severe first. |
| explain_issueD | An issue with its units and every claim recorded between them, and which record made it. |
| period_sequenceC | Which period lies directly over which, counted over the matrix: the site's sequence. |
| historyC | The interpretive edits made to the record, newest first. |
| propose_relationB | Record that |
| resolve_orderB | Settle a disputed pair: |
| assign_phaseC | Put units into a phase; warns if units of other phases lie between its members. |
| add_noteB | Attach an interpretive note to a unit (kept in the edit history). |
| revertB | Undo an edit from history(); the reversal is itself logged. |
| recheckC | Recompute matrix depth, contested claims and issues for a site. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools occupy clearly distinct niches: single-unit inspection (describe), set-based stratigraphy (below/above), pairwise comparison (relation), and specialized readouts (date_bracket, provenance, period_sequence). The only mild overlaps are describe vs below/above (direct neighbours vs full transitive sets) and issues vs explain_issue (list vs detail), both of which the descriptions resolve. Write tools (propose_relation, resolve_order, assign_phase, add_note) are semantically distinct rather than redundant.
All names are lowercase snake_case with no camelCase mixing, which keeps things readable. However the convention itself is split between bare imperative verbs (query, describe, revert, recheck) and noun labels (overview, issues, history, provenance), with compound verb_noun forms only in some cases (propose_relation, add_note). It is consistent in formatting but not in grammatical style.
Nineteen tools is on the heavy side, but the domain genuinely spans reads (overview, describe, relation, date_bracket, provenance), analysis (period_sequence, issues, explain_issue), and transactional writes (propose_relation, resolve_order, assign_phase, revert, recheck). Each tool maps to a distinct question an archaeologist would ask, so the count feels earned rather than padded.
The read and interpretive-write surface is thorough: navigable stratigraphy, dating, provenance, issue triage, edit history, and reversible edits. The clear gap is unit/site lifecycle — there is no create/update/delete for units or finds, and no export, so new stratigraphic records must come from outside the server. That is likely intentional for an interpretation layer over a Relate file, but it leaves a dead end for record-level changes.