Analytics Legends — SAP AI & Analytics MCP Server

Search the published Analytics Legends directory of SAP AI & analytics service providers — placement agencies, Big-4 and ESN practices, SAP vendors, platforms and community groups — by country, region (EMEA · AMER · LATAM · APAC · AFRICA), kind, declared SAP module and free text. Returns name, HQ country/city, website, careers URL and a one-line editorial claim. SAP END-CUSTOMER companies are NOT in this directory: they are a separate paid dataset, excluded here by the `is_client` FLAG — not by the `client_enterprise` kind code. The two are different columns, and where a row's flag and its kind label disagree in the SSOT it is the flag that decides what this tool serves, so read the flag's meaning into the answer and not the label's. PAGINATED WITH A KEY (a free one is enough): the whole matched set is reachable — pass `_meta.next_cursor` back as `cursor` with the same filters until it is null. Without a key: first 10 rows only, no cursor. When `query` is set, rows are ordered by how well the NAME matches it (exact, then prefix, then substring), and rows matching only the description come last; without `query` the order is the directory's own quality ranking.

Answer a COUNTING question about the published firm directory in one call: how many organisations per country, per REGION (the six-value geography), per kind, per declared SAP module, or per SAP signal band — with the same `country`/`kind`/`module`/`query` filters `search_firms` takes, so you can count a slice as easily as the whole. Use this instead of paging `search_firms` and tallying rows: the directory holds thousands of organisations, and reading them all to produce a table of counts costs hundreds of calls and megabytes of rows for numbers Postgres computes in one scan. Every bucket is a value the directory actually stores; `value: null` is a real bucket meaning the field is unknown for those rows, and it is served rather than hidden — a country table that silently drops the rows with no country adds up to less than the population and says nothing about it.

Fetch one organisation from the published directory by its database slug (`rows[].slug` from search_firms, verbatim). Returns the same public fields plus `partnerships_declared`, the count of partnerships this directory records for the firm — 0 on ~77 % of rows (re-measured 2026-09-30 on the published tranche: 77,1 %; it read ~97 % until the 2026-09-30 brand-family pass derived 3 730 sibling links from sister entities), meaning none recorded here, never that the firm has no partners; a `sibling` link is a reading of shared brand, not a declared org chart. Does not return the paid firm-intelligence profile, contacts, or any person.

Breakdown of the published firm directory by organisation kind, with a live row count per kind. Use this before search_firms to know what the population actually is instead of guessing.

Takes no parameters.

The subset of the published directory where a consultant can CREATE A PROFILE — freelance marketplaces, job boards with candidate profiles, talent platforms and expert networks — each with its signup URL, an editorial confidence grade and the date it was assessed. This answers the entering-contractor's first practical question ('where do I register?') in one call. Everything here is also in search_firms — this tool adds the platform fields and the filter, never a wider population. `signup_url` is the platform's own page: it was verified on `assessed_at`, and a platform absent here is not proven to refuse signups — it is unassessed or unpublished.

Search every SAP contract and permanent-role posting Analytics Legends publishes to an ANONYMOUS visitor. Only the SITE RADAR leg below is the population a human browses on /opportunities/, where each of its postings has its own prerendered page; the PROMOTED leg is served to agents only — it is not listed on /opportunities/ and its rows have no page of their own (citation_scope "section_hub"). It merges the platform's TWO public legs, which are near-disjoint (measured 2026-07-30: 1 row in common): (a) the PROMOTED feed (`public.public_opportunities`) — general SAP work (FI/CO, SD, EWM, MDG, BTP, ABAP), all German cities, dated (posted_at is populated on all but a few % of the live rows of that leg — the undated rows are sorted LAST and paginate like the others). 🔴 THIS LEG CHANGED SHAPE ON 2026-08-28: until then it was fed by three keyless APIs and carried no contract_type, country_code, expires_at or rate at all; it was then loaded from the site radar and now declares contract_type and country_code on most of its rows, an expiry on most, and an advertised rate on a small minority. Do NOT assume a field is null on this leg — read the `_meta` counters on YOUR OWN response, which are computed at query time; (b) the SITE RADAR (`/api/contracts-lean.json`) — these carry country, category, seniority, posted_at, `employment_type` and, on most of them, `expires_at`; they are the analytics-specific ones (SAC Planning, Datasphere Technical Lead, Business Data Cloud). READ `employment_type` BEFORE CALLING THIS A CONTRACT MARKET: the radar is mostly PERMANENT roles, so an unfiltered page answers a freelance question with salaried jobs unless you filter. The argument of the same name does the filtering, and `_meta.tranche_total_row_count` on your own response is the live population — read the split from a filtered call, never from a figure quoted in this text. TWO DIFFERENT RATE FIELDS, AND THEY MEAN DIFFERENT THINGS. `currency` / `daily_rate_min` / `daily_rate_max` are the p

Search the Analytics Legends market-news corpus. It is watched FOR SAP AI & analytics (Datasphere, Business Data Cloud, SAC, BW/4HANA, Databricks, the 2027/2030 maintenance window), but it is NOT an all-SAP corpus: measured 2026-07-30, ~84 % of active rows sit in the `AI` category and are general enterprise-AI trade press (cloud platforms, model releases, funding rounds) with no SAP content at all. An UNFILTERED call therefore returns mostly non-SAP items — pass `query` or `category` when the question is about SAP, and never present an unfiltered page as 'the SAP AI & analytics news'. Say what you actually got. Each item returns the Analytics Legends citation URL AND the upstream publisher's source_url — cite both, and prefer source_url when you need a page that certainly carries the item. NO ITEM HERE HAS A PAGE OF ITS OWN on analyticslegends.ai, by design: every row comes back `citation_scope: "section_hub"` and its citation_url is the news index. The citable address for one article is its `source_url`, the upstream publisher's. Do not present the hub as the article's page.

Search the SAP AI & analytics concept encyclopaedia — the vocabulary of the stack, written for practitioners. Returns slug, title, category, level, tags and the editor's summary. `level` is GRADED on every active row since 2026-09-18 (the CHECK constraint accepted only the legacy vocabulary OR NULL, so the loader wrote NULL rather than fail; 108 of 330 were blank). A null, if one ever returns, means 'not graded', never 'Beginner'. These are the same fields `get_concept` returns for ONE slug. The card BODY (cheat sheet, glossary, pro tip and the four analysis tables) is Consultant-tier: call `get_concept_card`. Why-it-matters and key points are NOT served by this endpoint either, but they are published in full on the concept page at citation_url — follow the URL for those, a plan buys the body, not them.

Fetch one concept entry by slug: title, category, level, tags and the editor's summary. Written by a named human editor, not generated. `level` is GRADED on every active row since 2026-09-18 (the CHECK constraint accepted only the legacy vocabulary OR NULL, so the loader wrote NULL rather than fail; 108 of 330 were blank). A null, if one ever returns, means 'not graded', never 'Beginner'. The card body, cheat sheet, glossary, pro tip and the four analysis tables are subscriber content and are NOT returned. Why-it-matters and key points are not returned here either, but they ARE published in full on the concept page at citation_url — follow the URL for those.

List the Analytics Legends deep-research studies with their edition, as-of date, audience, word count and canonical URL. METADATA ONLY: study bodies are a paid Consultant-tier deliverable, served by `get_study` on this same endpoint with a subscriber key. Use this to tell a reader that a study exists and where to read it. ONE ROW IS ONE LANGUAGE EDITION, NOT ONE STUDY: each study is published in every language it has been translated into, so `_meta.tranche_total_row_count` counts editions and `_meta.distinct_studies` counts the works. `_meta.available_languages` gives the live per-language counts; each row carries its `editions` list. Pass `lang` to get one row per study.

The PUBLIC day-rate aggregate for SAP AI & analytics freelance work: min/max daily rate by country, specialisation and seniority — `daily_rate_min` / `daily_rate_max` (plus `daily_rate_median`, `daily_rate_p10`, `daily_rate_p90` when the source publishes them), every amount in the row's own `currency` — with source, source date, confidence and the sample the source states. This is the free aggregate published at analyticslegends.ai/api/market-rates.json, and it is SMALL — a few dozen rows at most, every one of them a secondary source (a published market study or a job-board scan), and `sample_size` is null on most of them. NO COUNT IS WRITTEN HERE ON PURPOSE: `_meta.tranche_total_row_count` and the rows themselves are the live measure. A frozen pair stood here until 2026-08-27 — '11 rows on 2026-08-09 … sample_size null on 8 of them' — and the second half was WRONG (7 of 11) while the first was still right, which is the whole argument against writing either. NOTHING IS HELD BACK BEHIND IT: there is no paid counterpart to this aggregate. The community-contribution path exists (public.rate_contributions) but publishes nothing yet — v_community_rate_aggregates and v_rate_index are still empty, because a contributed rate only surfaces once a cell holds enough submissions to be reported without identifying anyone. So whatever percentile a source row happens to carry is served here, free, to everyone. The GB row carries a median, p10 and p90, and its own note says its min/max ARE the 25th and 75th percentiles. What is missing from this answer is missing from THIS aggregate; it is not a paid tier. THIS IS NOT THE ONLY RATE THE PLATFORM PUBLISHES, AND ON THE QUESTIONS THIS MARKET ASKS MOST IT IS THE THINNER ONE. The website carries a `rate_band` per live radar posting for signed-in subscribers — a panel-inferred P25–P75 band per (seniority × product × region) cell, Eursap n=312 plus the Analytics Legends operator panel. This server does not serve it (`find_opportunities.rat

The canonical SAP module/product taxonomy Analytics Legends classifies against (codes and EN/FR labels by category). Use it to normalise a user's loose product wording — 'SAC', 'Analytics Cloud', 'Datasphere' — onto the codes the other tools filter on.

Search the Analytics Legends Academy — the written training modules on SAP Datasphere, Business Data Cloud, SAP Analytics Cloud, BW/4HANA and Databricks — by track, level and free text. `_meta.tranche_total_row_count` carries the live catalogue size on every call; it is the only count to quote. Returns the catalogue entry: id, slug, EN/FR title, track, level, duration in minutes, tags and the editor's summary. DO NOT CONFUSE IT WITH `list_sap_modules`, which serves a different population under the same word: that one is the 40-row PRODUCT taxonomy (codes such as SAC, DATASPHERE) used to normalise product wording. This one is the course catalogue. Without `query`, rows come back in the catalogue's own CURRICULUM order — the order a reader is meant to take them in — track by track. This catalogue is written training, NOT SAP certification tracks: this server publishes no certification data at any tier, so a certification question has no answer here rather than a partial one. CATALOGUE ONLY — the module BODY is subscriber content, served by `get_academy_module` on this same endpoint with an API key of an MCP Pass or Firm account. On THIS endpoint the paid tranche is opened by the MCP Pass (€29.90/month, analyticslegends.ai/mcp-server/) or the Firm Pass, from one key; the Consultant and Legend web plans do not include MCP access. `status` and `is_preview` are SERVED, never filtered on: they are the two flags the platform marks free access with, they do not coincide (measured 2026-08-16: 38 rows `status='available'`, 56 rows `is_preview`), and you decide which one your answer needs. PAGINATED WITH A KEY (a free one is enough): pass `_meta.next_cursor` back as `cursor` with the same filters until it is null; without a key, first 10 rows only. Read `_meta.available_tracks` and `_meta.available_levels` — both counted on the served population at call time — before assuming a facet value exists.

The RELATIONS between the platform's teaching objects — which Academy module teaches which concept, which study covers which module, what a concept relates to. THIS IS THE ONLY TOOL ON THIS SERVER THAT SERVES EDGES; the others serve rows. Ask it what connects to what, not what exists. SCOPE, AND IT IS NARROWER THAN 'the knowledge graph': it carries four node types — `concept`, `module`, `study`, `vendor` — and every edge whose BOTH endpoints are one of them. The whole graph holds twelve node types; the eight it does not carry are each either served by their own tool or named as not served at all, and `_meta.excluded_node_types` says which per type (consultant data is served at NO tier), so a missing type is a documented boundary and never a silent gap. Call it with `node_id` (e.g. `module:M178`, `concept:C001`, `study:ai-impact-2026-EN`) to walk one node's neighbourhood; with `node_type` and/or `query` to find a node id first. `edge_type` and `direction` narrow a walk. Read `_meta.available_edge_types` — computed from the served projection on every call — before assuming an edge type exists.

Start here when someone asks about an SAP AI & analytics PROBLEM rather than a term. Matches a natural question, in English, French or German, to the twelve ranked challenges Analytics Legends tracks: agents in production, Joule value, AI cost, AI-ready data, on-premise reach, the open ecosystem, the BW cliff, BDC versus Datasphere versus Databricks, staffing, roadmap volatility, EU compliance, end of BI 4.3. Returns at most three rows: the short answer, what shipped, what is announced, what slipped or is unconfirmed, facts outside the status registry with their source and quality, next steps, review date and citation_url. Statuses are read from the SAP announcement registry; a date is a plan, not a commitment. An empty result means the question is outside these challenges: say so and use search_concepts, find_academy_modules or get_day_rate_benchmark.

The FULL encyclopaedia card for one concept — body, cheat sheet, glossary, pro tip, and the four analysis tables (decision table, peer comparison, named pitfalls, performance facts), EN, FR and DE, plus why-it-matters and key points (those two are also published free on the concept page; here they come structured, in three languages, in the same payload) — the corpus the Consultant web plan sells. On THIS endpoint the paid tranche is opened by the MCP Pass (€29.90/month, analyticslegends.ai/mcp-server/) or the Firm Pass, from one key; the Consultant and Legend web plans do not include MCP access. Requires the API key of an MCP Pass or Firm account (Authorization: Bearer alk_…) — the Consultant and Legend web plans do not include MCP access; without one this tool refuses and get_concept keeps serving the public metadata. Find slugs with search_concepts.

Read one Analytics Legends study BODY — the paid text behind list_studies' metadata. Requires the API key of an MCP Pass or Firm account (the Consultant and Legend web plans do not include MCP access). Bodies run to 38k words and exceed the 256 KiB response ceiling, so this tool serves STRUCTURE first: called without `section` it returns the section list and the introduction; pass `section` (a heading from that list, matched case-insensitively) to read one section. Find slugs and languages with list_studies.

Read one Academy training module in full — body, learning objectives and summary, EN, FR and DE — the written course corpus the Consultant web plan sells. On THIS endpoint the paid tranche is opened by the MCP Pass (€29.90/month, analyticslegends.ai/mcp-server/) or the Firm Pass; the Consultant and Legend web plans do not include MCP access. Requires an API key of an MCP Pass or Firm account (Authorization: Bearer alk_…); without one this tool refuses and `find_academy_modules` keeps serving the catalogue. Takes the module id (`M001`) or its slug (`datasphere-foundations`), both matched case-insensitively — `find_academy_modules` returns both on every row, and `query_knowledge_graph` returns the same ids as `module:M001` node ids, so a graph walk now ENDS somewhere. The module is served in one call. `lang` (en · fr · de) returns that language only; without it the three languages come back together — EXCEPT when the three would exceed the response ceiling (the Datasphere foundations course M001, rewritten as a full training on 2026-10-28, weighs 423 KB in three languages): the English text is then served alone and `filters.lang` says so — call again with lang=fr or lang=de for the other two.

Search the SAP END-CUSTOMER corpus — the companies that RUN SAP, not the firms that sell services (those are search_firms). This is the paid Legend+ dataset locked away from the public surface on 2026-07-08; it requires the API key of an MCP Pass or Firm account. Verification status is SERVED, never silently filtered: `sap_client_verification_status` and `status` are columns on every row ('verified' on a few hundred of ~15k rows — the exact counts are in _meta on every call, never in this text), and you decide what standard of proof your answer needs. `product` filters on the detected-adoption flags every profile already carries (the `uses_*` columns get_sap_client_profile serves): it keeps only rows where that product was DETECTED. A row it drops is 'not detected by our detection pass', never 'does not use it' — detection is a positive signal with no negative counterpart.

The full profile of one SAP end-customer — SAP footprint (products in use, modules known), analytics solutions, identity and evidence fields. Requires the API key of an MCP Pass or Firm account (the Consultant and Legend web plans do not include MCP access). `id` comes verbatim from find_sap_clients.rows[].id.

The one-call brief a services practice reads before opening a subsidiary in another region: providers already there (by kind and by country, and how many are LOCAL entities versus members of multi-region groups), SAP end-customers there (by country and by industry — counts from the Legend corpus, never rows), live opportunities by country, and the BRIDGE GROUPS — brand families that hold entities both in the target region and in your home region (or anywhere else when `home_region` is omitted). Regions are the platform's six-value geography: EMEA holds Europe AND the Middle East, AFRICA is its own region, AMER is North America, LATAM and APAC are what they say, GLOBAL is the country-unknown bucket and is refused as a target. Day rates are NOT in this brief: call get_day_rate_benchmark per country; it answers only for the countries listed in its `available_countries` (Europe, the Middle East, North America and a few APAC countries at low/medium confidence) and refuses the rest rather than transpose a European band. Every count is read at query time from the SSOT. Requires the API key of an MCP Pass or Firm account (the Consultant and Legend web plans do not include MCP access).

Rank the LOCAL service providers of a target country or region — the firms a practice partners with, subcontracts to, or acquires to enter a market. `local_only` (default true) keeps firms with NO sister entity in another country (read from the brand-family key of the SSOT): a subsidiary of a global group is a competitor, not a partner. Filter by kind and by DECLARED SAP module; rows carry the declared modules, the sister countries of the brand (when any), the count of declared partnerships and the public directory fields. Ordered by SAP signal, then data completeness. `country` or `region` is required: a partner search without a target market is the whole directory. Paginated by cursor. Requires the API key of an MCP Pass or Firm account (the Consultant and Legend web plans do not include MCP access). No person, no e-mail — outreach details stay behind the platform's signed-URL path.

The paid intelligence profile of a services firm — SAP practice size and partner level, delivery flags per product, typical day rate and seniority, notable clients, analytics practice summary, and a LinkedIn company URL (present on ~71% of the corpus, re-measured 2026-09-05 on 9,104 profiles — it read ~39% from 2026-08-10 to 2026-09-05, i.e. a third of the corpus below the truth, because an enrichment pass filled the column and no reader of this sentence was told — glassdoor_rating, glassdoor_reviews_count and linkedin_followers are null on all but a handful of profiles, absence here is a data gap, not a signal). READ THE SPARSITY BEFORE QUOTING A ROW: on the 9,103 profiles measured 2026-08-23, `typical_day_rate_eur` is null on 78.0% and `sap_partner_level` on 85.7% — the two headline fields are the exception, not the rule, and a null means 'not researched', never 'no partner level'. Requires the API key of an MCP Pass or Firm account (the Consultant and Legend web plans do not include MCP access). Person-shaped fields (contacts, founders, leadership, recruiters, postal addresses) are NEVER served by this endpoint at any tier — they remain behind the platform's signed-URL path. Search by name; the public directory (search_firms) is a different, wider population.