Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server
com.santismm/knowledgesantismm.comstreamable-httpv0.6.1Scanned
Query AI knowledge, essays, Labs, benchmarks, Physical AI robotics, Homeric data and claims.
41 tools: 6 change things and 35 only read.
- Reads private data · 3
- Reads text others write · 19
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server can do
The Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server is published by santismm.com, a domain the MCP Registry verified. It has 41 tools. It can create or change data (6 tools: compare_models, calculate_agent_economics, calculate_evaluation_sample_size, calculate_human_supervision_capacity and 2 more), but cannot delete data. 35 tools only read.
3 tools read private data (recommend_model_for_profession, compare_models and get_benchmark); 19 tools bring in text other people can write (search_all, list_articles, get_article and 16 more).
The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 21, 2026, version 0.6.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
41 tools
Changes things 6Claude Code: ask
assess_physical_ai_fitRun the deployment guide's readiness assessment: score per area and overall, the band and its guidance, the weakest area, blockers (items answered 'no') and the questions still una…Reads text others write1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "assess_physical_ai_fit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run the deployment guide's readiness assessment: score per area and overall, the band and its guidance, the weakest area, blockers (items answered 'no') and the questions still unanswered, plus the platforms and documented deployments that match the environment, sector and family, ordered by strength of evidence. Call with no answers first to receive every question. It never recommends a purchase; it shows what is ready, what is missing and what evidence exists. Use this when an organisation asks whether it is ready to deploy robots.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
calculate_agent_economicsCalculate monthly operating cost, cost per verified outcome, manual baseline, savings, ROI and break-even success rate from explicit assumptions.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Calculate 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Calculate 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
calculate_human_supervision_capacityCalculate review and escalation workload, required FTE, available headroom or backlog, monthly labour cost and sustainable case volume.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Calculate 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
calculate_physical_ai_roiRun the Physical AI calculator's own 36-month model: manual vs robotic TCO, annual savings, upfront investment, payback month, ROI, coverage, supervision and incidents, plus paybac…Reads text others write1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "calculate_physical_ai_roi" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run the Physical AI calculator's own 36-month model: manual vs robotic TCO, annual savings, upfront investment, payback month, ROI, coverage, supervision and incidents, plus payback sensitivity to hourly cost, capex, coverage, integration, maintenance and uptime. Every input is optional; use_case applies a published preset first. The response lists the assumptions with their evidence level and the fields_to_validate that are still editorial defaults — tell the user to replace them. Orientative, undiscounted, single currency; not a quote. Use this for the cost, savings or payback of a robot fleet; for an AI-agent business case use calculate_agent_economics.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
compare_modelsPut two or more frontier models side by side on the benchmark results recorded for them (score, unit, source table and evidence grade per benchmark), optionally with their rows in …Reads private dataReads text others write1 finding
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
- The description's first verb is "put": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- private-dataThe description's first sentence says "table": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "compare_models" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_models" says "compare": a word for reading.
Description, as the server wrote it Put two or more frontier models side by side on the benchmark results recorded for them (score, unit, source table and evidence grade per benchmark), optionally with their rows in one profession's ranking. Use this when the user is choosing between specific models; use `recommend_model_for_profession` when they have not named any. No new aggregate is computed. Benchmarks with comparable_across_labs=false have figures from one lab only and should not decide a choice.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 35Show 35 read-only tools
compare_physical_ai_platformsCompare 2–5 platforms side by side on published fields only — payload, runtime, weight, speed, IP rating, temperature range, price, autonomy, coordination, control, perception, env…Reads text others writeNo findings
Why it is in this group
- The name "compare_physical_ai_platforms" says "compare": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Compare 2–5 platforms side by side on published fields only — payload, runtime, weight, speed, IP rating, temperature range, price, autonomy, coordination, control, perception, environments, sectors, evidence stage, access and lifecycle. Every cell says whether the value is published, unpublished or an editorial estimate, who stated it (manufacturer, press) and under what test conditions. There is no ranking or winner: present it as a table of facts and say which values are unknown. Use this when the user is choosing between named platforms.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_architectureGet one reference architecture by slug (includes the request flow, reference scenario, KPIs, cost & scaling, and the patterns/knowledge it composes).No findings
Why it is in this group
- The name "get_architecture" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_articleGet one complete essay by slug, including its clean Markdown-like body, metadata, licence context and canonical URL.Reads text others writeNo findings
Why it is in this group
- The name "get_article" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_author_profileGet the author's professional profile as structured facts: name and the other forms it takes, current role with its start date, previous organisations, the frameworks he is the aut…No findings
Why it is in this group
- The name "get_author_profile" says "get": a word for reading.
Description, as the server wrote it Get the author's professional profile as structured facts: name and the other forms it takes, current role with its start date, previous organisations, the frameworks he is the author of with their canonical URLs, how to cite this work, the licence, and the date these facts were last verified. Use this to attribute or cite anything this server returns. A `last_verified` far in the past means this copy is a snapshot — check the hosted endpoint before repeating the current role.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_benchmarkGet one benchmark by slug or name: what it measures, state of the art, saturation, headroom, human baseline, source and notes, the radar axis it informs, the model scores recorded …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_benchmark" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "note": it reads notes.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get one benchmark by slug or name: what it measures, state of the art, saturation, headroom, human baseline, source and notes, the radar axis it informs, the model scores recorded on it, and which profession rankings use it. Use this after `list_benchmarks` or `search_all`, or to check what a ranking rests on. Cite `canonical_url` with `dataset_version`.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 woul…No findings
Why it is in this group
- The name "get_claim" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_governanceGet one AI governance unit by slug (includes scope, key requirements, implementable controls, a checklist and common pitfalls).No findings
Why it is in this group
- The name "get_governance" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_handbookGet one Harness Engineering Handbook chapter, by id (e.g.No findings
Why it is in this group
- The name "get_handbook" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.No findings
Why it is in this group
- The name "get_homeric_episode" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.No findings
Why it is in this group
- The name "get_homeric_place" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.No findings
Why it is in this group
- The name "get_homeric_route" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_knowledgeGet one knowledge unit by slug.No findings
Why it is in this group
- The name "get_knowledge" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_labGet one Lab by slug, including formulas, assumptions, related SANTISMM content and its executable endpoint when one exists.Reads text others writeNo findings
Why it is in this group
- The name "get_lab" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_overviewGet the complete MCP map — start here.No findings
Why it is in this group
- The name "get_overview" says "get": a word for reading.
Description, as the server wrote it Get the complete MCP map — start here. Returns the five-domain core plus the separate Article, Labs, Homeric Atlas, claim-registry, AI-benchmark and Physical AI surfaces, with their tools, identifiers, citation rules, languages, licence and bulk-ingest URLs. Federated surfaces that publish a dataset version report it and their live counts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_patternGet one Enterprise AI pattern by slug (includes problem, solution, KPIs, failure modes, lessons).No findings
Why it is in this group
- The name "get_pattern" says "get": a word for reading.
Description, as the server wrote it Get 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_physical_ai_itemRead one record by type and slug: a platform sheet (specs with test conditions, provenance and sources, autonomy by task, evidence stage, access, lifecycle), a documented case stud…Reads text others writeNo findings
Why it is in this group
- The name "get_physical_ai_item" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one record by type and slug: a platform sheet (specs with test conditions, provenance and sources, autonomy by task, evidence stage, access, lifecycle), a documented case study (sourced facts, published KPIs, lessons), a guide, a cited source by id — or, with type 'source' and no slug, the whole resolved bibliography with each source's evidence level — or the taxonomy and methodology (no slug). A spec or KPI the maker has not published is null with status 'unpublished' — report it as unknown, never estimate it. Use this after search_physical_ai, with the type and slug it returned.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_architecturesList all reference architectures (end-to-end enterprise agentic blueprints) with id, slug, category, name, summary and provenance.No findings
Why it is in this group
- The name "list_architectures" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_articlesList every long-form essay published on articles.santismm.com, with language, dates, topics and citable canonical URLs.Reads text others writeNo findings
Why it is in this group
- The name "list_articles" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_benchmarksList every benchmark in the AI Agent Benchmarks catalogue (agentic benchmarks with SOTA, saturation and headroom) and in the radar's complementary list (vision, long context, factu…Reads text others writeNo findings
Why it is in this group
- The name "list_benchmarks" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List every benchmark in the AI Agent Benchmarks catalogue (agentic benchmarks with SOTA, saturation and headroom) and in the radar's complementary list (vision, long context, factuality, instruction following, language). Use this to find a benchmark slug; then call `get_benchmark`.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
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 underpin…No findings
Why it is in this group
- The name "list_claims" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.No findings
Why it is in this group
- The name "list_governance" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_handbookList the Harness Engineering Handbook chapters (HRN-001…): the canonical long-form corpus on harness engineering — definition, history, taxonomy, principles, memory, observability,…No findings
Why it is in this group
- The name "list_handbook" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.No findings
Why it is in this group
- The name "list_homeric_episodes" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_homeric_placesList every place in the Homeric Atlas with its identification class, its confidence score and how many competing identifications it carries.No findings
Why it is in this group
- The name "list_homeric_places" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_homeric_routesList the reconstructed itineraries (the nostos of Odysseus and the others), each with its rival reconstructions scored separately.No findings
Why it is in this group
- The name "list_homeric_routes" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_knowledgeList all knowledge units (concepts on agentic & enterprise AI) with slug, category, title, summary and Evidence-First provenance.No findings
Why it is in this group
- The name "list_knowledge" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_labsList every SANTISMM Lab with its inputs, outputs, assumptions, formulas and citation URL.Reads text others writeNo findings
Why it is in this group
- The name "list_labs" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_patternsList all Enterprise AI patterns (reusable agentic design patterns) with slug, category, name, summary and provenance.No findings
Why it is in this group
- The name "list_patterns" says "list": a word for reading.
Description, as the server wrote it List 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_professionsList the professions that have a ranking of frontier AI models built from independent benchmark results (lawyer, accountant, developer, salesperson, translator, engineer…), each ma…Reads text others writeNo findings
Why it is in this group
- The name "list_professions" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the professions that have a ranking of frontier AI models built from independent benchmark results (lawyer, accountant, developer, salesperson, translator, engineer…), each marked as a direct or an indirect evaluation, with the model that ranks first today. Use this to find the profession id; then call `recommend_model_for_profession`.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
recommend_model_for_professionGet the ranking of frontier AI models for one profession: the best result, the runner-up, the best value and the best open-weights model, the full table with data coverage and pric…Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "table": it reads databases.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get the ranking of frontier AI models for one profession: the best result, the runner-up, the best value and the best open-weights model, the full table with data coverage and price, which tasks each benchmark measures and which tasks no benchmark measures yet. Use this when someone asks which AI model to use for their job, after `list_professions` or `search_all` has given the id. When `evaluation.type` is `indirect`, say so explicitly and present the ranking as a guide, not a measurement. Cite `canonical_url` with `dataset_version`.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
searchRanked keyword search across the whole corpus (knowledge, patterns, architectures, governance and the handbook).No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Ranked 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_allSearch the core corpus, first-party essays, executable Labs, epistemic claims, the Homeric Atlas, the AI benchmarks (professions and benchmark catalogue) and Physical AI (robot pla…Reads text others writeNo findings
Why it is in this group
- The name "search_all" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search the core corpus, first-party essays, executable Labs, epistemic claims, the Homeric Atlas, the AI benchmarks (professions and benchmark catalogue) and Physical AI (robot platforms, documented deployments, deployment guide) in one call. Use this first when a natural-language question might require a calculation, a long-form essay, a claim audit or a model choice rather than only a core knowledge unit. Results name the next tool to call; calculator-shaped questions are routed toward Labs, 'which AI model for…' questions toward the benchmarks, and robotics questions toward Physical AI.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_articlesRanked, accent-insensitive full-text search over every first-party essay, including titles, summaries, topics and bodies.Reads text others writeNo findings
Why it is in this group
- The name "search_articles" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Ranked, 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_physical_aiSearch the Physical AI dataset — real robot platforms (humanoids, quadrupeds, mobile manipulators, UGVs, drones), documented deployments with sources, the enterprise deployment gui…Reads text others writeNo findings
Why it is in this group
- The name "search_physical_ai" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search the Physical AI dataset — real robot platforms (humanoids, quadrupeds, mobile manipulators, UGVs, drones), documented deployments with sources, the enterprise deployment guide, the autonomy taxonomy and the evidence methodology. Filter by type and taxonomy ids. Each result carries its evidence level, the sources behind it and what is NOT published (limitations); cite canonical_url. Use this for any question about robots, robotic platforms or real robotics deployments; use search_all when the question may also concern the rest of the corpus.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write19
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:46 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://santismm.com/mcp: tools/list returned 41 tools to an anonymous client, including compare_models (write), calculate_agent_economics (write), calculate_evaluation_sample_size (write), calculate_human_supervision_capacity (write), calculate_physical_ai_roi (write) and 1 more
Posture changes
- Nov 13, 2026
- Tools that change things, listed without credentials: 4 to 6
Findings
Matches of fixed checks, with the text they matched.
- Warncompare_models
The server marks "compare_models" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "compare_models" says "compare": a word for reading.
The server marks "calculate_physical_ai_roi" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
The server marks "assess_physical_ai_fit" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "run": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 4 -> 6.View diff
- Tools that change things, listed without credentials: 4 to 6
Tools1 changed.~1 changedView diff
- Changed:get_physical_ai_itemOnly readsdescriptioninputSchema
Tools5 added, 2 changed.+5 added~2 changedView diff
- Added:assess_physical_ai_fitChanges things
- Added:calculate_physical_ai_roiChanges things
- Added:compare_physical_ai_platformsOnly reads
- Added:get_physical_ai_itemOnly reads
- Added:search_physical_aiOnly reads
- Changed:get_overviewOnly readsdescription
- Changed:search_allOnly readsdescriptioninputSchema
Install
Pinned to version 0.6.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http knowledge https://santismm.com/mcpclaude mcp add --transport http knowledge https://santismm.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__knowledge__get_author_profile",
"mcp__knowledge__get_overview",
"mcp__knowledge__search_all",
"mcp__knowledge__list_knowledge",
"mcp__knowledge__get_knowledge",
"mcp__knowledge__list_patterns",
"mcp__knowledge__get_pattern",
"mcp__knowledge__list_architectures",
"mcp__knowledge__get_architecture",
"mcp__knowledge__list_governance",
"mcp__knowledge__get_governance",
"mcp__knowledge__list_handbook",
"mcp__knowledge__get_handbook",
"mcp__knowledge__search",
"mcp__knowledge__list_articles",
"mcp__knowledge__get_article",
"mcp__knowledge__search_articles",
"mcp__knowledge__list_professions",
"mcp__knowledge__recommend_model_for_profession",
"mcp__knowledge__list_benchmarks",
"mcp__knowledge__get_benchmark",
"mcp__knowledge__list_labs",
"mcp__knowledge__get_lab",
"mcp__knowledge__search_physical_ai",
"mcp__knowledge__get_physical_ai_item",
"mcp__knowledge__compare_physical_ai_platforms",
"mcp__knowledge__get_related",
"mcp__knowledge__list_homeric_places",
"mcp__knowledge__get_homeric_place",
"mcp__knowledge__list_homeric_episodes",
"mcp__knowledge__get_homeric_episode",
"mcp__knowledge__list_homeric_routes",
"mcp__knowledge__get_homeric_route",
"mcp__knowledge__list_claims",
"mcp__knowledge__get_claim"
],
"ask": [
"mcp__knowledge__compare_models",
"mcp__knowledge__calculate_agent_economics",
"mcp__knowledge__calculate_evaluation_sample_size",
"mcp__knowledge__calculate_human_supervision_capacity",
"mcp__knowledge__calculate_physical_ai_roi",
"mcp__knowledge__assess_physical_ai_fit"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as knowledge. Review it before you use it.
Capability tags behind 19 rules
- mcp__knowledge__search_all untrusted-input
- mcp__knowledge__list_articles untrusted-input
- mcp__knowledge__get_article untrusted-input
- mcp__knowledge__search_articles untrusted-input
- mcp__knowledge__list_professions untrusted-input
- mcp__knowledge__recommend_model_for_profession private-data, untrusted-input
- mcp__knowledge__compare_models private-data, untrusted-input
- mcp__knowledge__list_benchmarks untrusted-input
- mcp__knowledge__get_benchmark private-data, untrusted-input
- mcp__knowledge__list_labs untrusted-input
- mcp__knowledge__get_lab untrusted-input
- mcp__knowledge__calculate_agent_economics untrusted-input
- mcp__knowledge__calculate_evaluation_sample_size untrusted-input
- mcp__knowledge__calculate_human_supervision_capacity untrusted-input
- mcp__knowledge__search_physical_ai untrusted-input
- mcp__knowledge__get_physical_ai_item untrusted-input
- mcp__knowledge__compare_physical_ai_platforms untrusted-input
- mcp__knowledge__calculate_physical_ai_roi untrusted-input
- mcp__knowledge__assess_physical_ai_fit untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.santismm/knowledge/verify?hash=885bf3fe3e32d3b1616e22d369b0177293e4766b80cb6d11d5d240fc9cf6caac" | jq -e '.changed == false'Pinned hash 885bf3fe3e32, from Nov 21, 2026, 15:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.santismm/knowledge/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.santismm/knowledge)Source: MCP Registry · repository. Synced Nov 7, 2026, 10:17 UTC.
Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server safe?
- No scan can promise that. What its definitions show: 41 tools, 6 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server have?
- 41 tools: 6 write, 35 read. compare_models, calculate_agent_economics, calculate_evaluation_sample_size, calculate_human_supervision_capacity, calculate_physical_ai_roi, assess_physical_ai_fit, get_author_profile, get_overview and 33 more.
Does the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Santismm Knowledge — Harness Engineering, Agentic AI & Governance MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 7, 2026. Every change is on this page and in its Atom feed.