Query this corpus natively from any AI agent
The Santismm Knowledge Platform is exposed as a public MCP server over Streamable HTTP. Resources read complete, citable content; 30 tools search, navigate and execute five core domains, first-party essays, Labs, the Homeric Atlas and the epistemic claim registry.
Streamable HTTP (JSON-RPC)
Stateless Streamable HTTP: no session, no API key, nothing to install. The endpoint serves both protocol eras, so an existing client that sends initialize keeps working exactly as it did and nothing you have configured needs changing.
Protocol details — only if you use revision 2026-07-28 or call from a browser
On revision 2026-07-28 there is no initialize handshake. Each request declares itself with MCP-Protocol-Version: 2026-07-28, Mcp-Method, and Mcp-Name for a tool call. It also carries a params._meta envelope with io.modelcontextprotocol/protocolVersion, .../clientInfo and .../clientCapabilities; an empty object is a valid capabilities value, but the key is required and its absence is a 400. Headers and body are cross-checked, so a request whose headers disagree with its body is refused rather than guessed at.
Browser clients are accepted only from santismm.com, www.santismm.com and localhost; any other Origin gets a 403 before the transport is touched. The CORS headers stay open on purpose, so a rejected page can read that 403 instead of an opaque network error. Non-browser clients send no Origin and are unaffected.
Read content without executing a tool
Use resources/list and resources/templates/list to discover stable santismm:// addresses, then resources/read for the complete JSON document. Every payload retains its public canonical_url for citation. Federated Article and Lab templates stay available even if their remote catalogue is temporarily down.
santismm://overviewRead the corpus map, licences, languages, extensions and bulk-ingest URLs.
santismm://knowledge/{locale}/{slug}Read one complete knowledge unit, localised and carrying provenance plus canonical citation URLs.
santismm://patterns/{locale}/{slug}Read one complete patterns unit, localised and carrying provenance plus canonical citation URLs.
santismm://architectures/{locale}/{slug}Read one complete architectures unit, localised and carrying provenance plus canonical citation URLs.
santismm://governance/{locale}/{slug}Read one complete governance unit, localised and carrying provenance plus canonical citation URLs.
santismm://handbook/{locale}/{id}Read one complete Handbook chapter by stable id or slug and locale.
santismm://articles/{slug}Read one complete first-party essay from the canonical Articles API.
santismm://labs/{slug}Read one calculator, converter, experiment or educational-game definition without executing it.
santismm://homeric/{kind}/{locale}/{slug}Read one place, episode or route with competing identifications and rubric evidence.
santismm://claims/{locale}/{id}Read one load-bearing claim, including limits and falsification criteria.
Start from a workflow instead of a blank call
Use prompts/list to see the workflows this server ships, then prompts/get to render one. locate_in_corpus searches every surface before fetching, locate_handbook_chapter hands over the real chapter identifiers instead of telling you not to guess, and cite_with_provenance walks a citation through its canonical URL, evidence block and the claim behind it.
locate_in_corpusFind which surface holds a concept before fetching it. Searches every surface first, so a slug that lives in one domain is not requested from another.
locate_handbook_chapterHands over the real chapter identifiers and their titles, so a chapter is requested by an id that exists rather than one inferred by analogy.
cite_with_provenanceProduce a citation that carries the canonical URL, the Evidence-First block and — when the statement is load-bearing — the epistemic level and retraction condition of the claim behind it.
Search, navigate and calculate
Use tools when the agent needs routing, ranked retrieval, graph traversal or deterministic execution. Tool results link back to the matching Resource URI whenever the result is readable content.
get_overviewGet the complete MCP map — start here. Returns the five-domain core plus the separate Article, Labs, Homeric Atlas and claim-registry surfaces, with their tools, identifiers, citation rules, languages, licence and bulk-ingest URLs.
search_allSearch the core corpus, first-party essays, executable Labs, epistemic claims and the Homeric Atlas in one call. Use this first when a natural-language question might require a calculation, a long-form essay or a claim audit rather than only a core knowledge unit. Results name the next tool to call; calculator-shaped questions are routed toward Labs.
list_knowledgeList all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance. Use this to browse the domain; use search when you have a question rather than a slug.
get_knowledgeGet one knowledge unit by slug. Returns the full entry, or a single-locale body if locale is given. Use this once search or list_knowledge has given you a slug.
list_patternsList all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance. Use this to browse the catalogue; use search when you are looking for a pattern that solves a problem.
get_patternGet one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons). Use this once search or list_patterns has given you a slug.
list_architecturesList all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance. Use this to browse the blueprints; use search when you have a use case rather than a name.
get_architectureGet one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes). Use this once search or list_architectures has given you a slug.
list_governanceList all AI governance units (regulations, standards, frameworks, playbooks — EU AI Act, ISO 42001, NIST AI RMF, agentic checklist) with id, slug, category, name and summary. Use this to browse the regulations and standards; use search for an obligation or control.
get_governanceGet one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls). Use this once search or list_governance has given you a slug.
list_handbookList the Harness Engineering Handbook chapters (HRN-001…): the canonical long-form corpus on harness engineering — definition, history, taxonomy, principles, memory, observability, evaluation, governance, planning, orchestration, security, case studies, glossary and bibliography. Use this to see the chapter map; use search when you have a topic rather than a chapter.
get_handbookGet one Harness Engineering Handbook chapter, by id (e.g. 'HRN-001') or slug. Returns the full Markdown body plus its provenance and related ids. Use this once search or list_handbook has given you an id.
searchRanked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook). Matches every language and ignores accents, so query in the user's own words. Each hit carries a relevance score and the fields it matched; follow up with the matching get_* tool for full detail. Use this before any get_* tool whenever you have a question rather than an identifier.
list_articlesList every long-form essay published on articles.santismm.com, with language, dates, topics and citable canonical URLs. Use this to browse the essay catalogue; use search_articles when you have a topic rather than a slug.
get_articleGet one complete essay by slug, including its clean Markdown-like body, metadata, licence context and canonical URL. Use this after list_articles or search_articles has returned the slug you need.
search_articlesRanked, accent-insensitive full-text search over every first-party essay, including titles, summaries, topics and bodies. Use this when you need long-form analysis about a topic; follow with get_article for the complete essay.
list_labsList every SANTISMM Lab with its inputs, outputs, assumptions, formulas and citation URL. Use this to discover interactive and machine-readable tools; filter by kind when the user specifically asks for a calculator, converter, experiment or educational game.
get_labGet one Lab by slug, including formulas, assumptions, related SANTISMM content and its executable endpoint when one exists. Use this after list_labs or search_all; use the named calculate_* tool rather than reimplementing a published formula.
calculate_agent_economicsCalculate monthly operating cost, cost per verified outcome, manual baseline, savings, ROI and break-even success rate from explicit assumptions. Use this for an agent business case or scenario comparison; keep every monetary input in the same currency and cite the returned canonical_url.
calculate_evaluation_sample_sizeCalculate two different samples: how many independent evaluations are needed to detect at least one failure, and how many are needed to estimate its rate at a chosen margin. Use this when a user asks how many tests are enough; do not interpret zero observed failures as proof of zero risk.
calculate_human_supervision_capacityCalculate review and escalation workload, required FTE, available headroom or backlog, monthly labour cost and sustainable case volume. Use this before production rollout to test whether the stated human-oversight model is operationally credible; the result uses averages and is not a queueing simulation.
get_relatedTraverse the knowledge graph: given a unit, return its neighbours — the units it links to (outgoing) and the units that reference it (incoming), each with the relationship type. Use this after a get_* call to widen an answer with adjacent units.
list_homeric_placesList every place in the Homeric Atlas with its identification class, its confidence score and how many competing identifications it carries. Use this to browse the atlas; use get_homeric_place once you have a slug. Identification classes: accepted (an excavated site with consensus), plausible (a real place, contested), speculative (a minority reading or a later tradition), mythical (the poem places it outside the mappable world). Confidence is a published 0-12 rubric - textual, archaeological, scholarly and geographic, 0-3 each - and is an editorial judgement, not a probability.
get_homeric_placeGet one place by slug: every identification proposed for it, each with its own coordinates, class, 0-12 rubric and sources, plus the attested passages. Use this when you need to weigh the evidence for a location, or to cite it; a place the poem does not locate carries no coordinates at all.
list_homeric_episodesList every episode of the Iliad and the Odyssey held in the atlas, in reading order, with its passage, the places it involves and how firmly it can be located. Use this to find the episode you want; use get_homeric_episode for its theories and sources.
get_homeric_episodeGet one episode by slug: the passage, the narrative, the competing theories about where it happened (each with its proponent and sources), the confidence rubric and the FAQs. Use this when the question is where an episode took place and who argued for it.
list_homeric_routesList the reconstructed itineraries (the nostos of Odysseus and the others), each with its rival reconstructions scored separately. Use this to see which voyages the atlas reconstructs before fetching one.
get_homeric_routeGet one route by slug: each reconstruction variant with its ordered stops, the hypothesis chosen at each stop, its confidence rubric and its sources. Use this to compare rival reconstructions of a voyage: they are returned side by side rather than merged.
list_claimsList the load-bearing claims of the corpus, each tagged as observed_fact, industry_synthesis, santismm_thesis or strategic_hypothesis, with its confidence and the units it underpins. Use this before quoting the handbook to know whether a statement is evidence, a reading of the industry, or a position taken. Filter by claim_type to get only what is checkable.
get_claimGet one claim by id (HE-CLAIM-001) or slug: the statement, what it rests on, its structured sources, and — always present — what it does NOT establish and the observation that would retire it. Use this to cite the corpus honestly, or to check whether a result you have just measured confirms or falsifies a claim it makes.
Add it to your MCP client
Most MCP clients (Claude Desktop, IDE extensions, custom agents) accept an HTTP MCP server in their config. Paste:
{
"mcpServers": {
"santismm-knowledge": {
"type": "http",
"url": "https://santismm.com/mcp"
}
}
}Three ways to reach the same corpus
The hosted endpoint needs nothing installed. Both packages run the same server locally over stdio — the difference is where the corpus lives, and it decides which one you want.
| How | Corpus | Freshness |
|---|---|---|
| https://santismm.com/mcp | remote | always current |
| npx santismm-knowledge-mcp | core bundled; Articles and Labs online | frozen at publish time |
| uvx santismm-knowledge-mcp | none — proxies to the endpoint | always current |
The npm package is a snapshot on purpose, so it can be behind. It says so: get_overview reports the newest unit date of the copy answering, and a not_found repeats it, so an agent can tell a wrong identifier from a corpus older than what it is asking for.
Five core domains: knowledge, patterns, architectures, governance and the Harness Engineering Handbook. search_all routes natural-language questions across the core, Articles, executable Labs and claims; dedicated tools expose the Homeric Atlas.
Traverse links with get_related, the same graph behind /api/graph.json.
Every unit carries Evidence-First provenance (evidence level, confidence, source types).
Every tool declares an outputSchema and returns validated structuredContent, so results arrive as typed data — the serialized JSON stays in content for older clients.
The same server, elsewhere
This server is one thing with several front doors. Each of these is the same endpoint and the same corpus, declared as sameAs in the page metadata so a crawler can reconcile them instead of counting separate projects.
Not using MCP?
The core corpus and associated datasets are also published as plain text and JSON. Every direct entry point advertised by the live discovery manifest is linked from For AI agents: