All servers / Finance / BICon MCP server
BICon MCP server
BICon Composer Analyst: MCP server that helps an AI client compose a valid BICon portfolio initiative as an import file, and analyse the portfolio read-only,
Tested by ConnectATDScore 85 out of 100. Tested 2026-11-19 on package version 0.30.0. Package: @bicon/mcp-composer · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 19 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 8 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (3.5 seconds including download)
- Tools offered: 15
- Last published: 2026-11-14
- Weekly downloads (npm): 667
- License: UNLICENSED · Direct dependencies: 1
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
composer_versionno parametersReturns the running Composer's version and capabilities. Call it when a SUCCESSFUL tool result lacks `composerVersion` (a stale instance) — SDK-level input rejections ('Input validation error …') never carry it and are not a sign of staleness.
get_initiative_schemano parametersReturns the field catalog: required fields, enum values, the four dimensions with their named sub-dimensions (rate each 0–100) and confidence scale, portfolio-mode wording overlays, optional sections with their exact shapes, the EU-AI-Act vocabularies, and the import handoff steps. Call this first.
read_portfolio_context1 of 1 parameter describedTurns the organisation's portfolio-context file (downloaded in the BICon Portfolio Steering app: Import/Export → 'Download portfolio context') into the interview plan for THIS organisation: its own labels, help texts and rating notes for the sub-dimensions, which sub-dimensions are switched off (do not ask, not scored), its business units, categories, tags, skills (id + name), initiatives (id + name) and the capability map's capabilities (id, name, domain, importance, current → target maturity), currency, discount rate and whether the EU-AI-Act module is on — plus a short contextId. Call it right after get_initiative_schema: with the file when the user provides it, or WITHOUT `context` when live access is set up (the Composer then builds the same context from the app); then pass `context: "<contextId>"` to assemble_initiative and export_initiative_file.
assemble_initiative28 of 45 parameters describedTurns a compact spec (metadata + named sub-dimension ratings + confidence per dimension + optional sections, plus the organisation's `context` — contextId or file — when the user provided it) into a fully-formed, contract-valid initiative. Mints the id and timestamps (pass `id` only to UPDATE an existing initiative), DERIVES the four dimension scores (mean of the enabled subs) and validates against the API contract and — with context — the organisation's own lists and ids. Returns {ok, initiative, derivedScores, warnings, errors, contextId}. On errors, fix the listed fields and call again. Show derivedScores (and warnings) to the user before exporting.
export_initiative_file5 of 5 parameters describedAssembles the SAME compact spec (and context) you passed to assemble_initiative and wraps the result in the app's single-initiative JSON envelope. Returns {ok, filename, json, importInstructions, derivedScores, warnings}. Save `json` under `filename`; the user imports it via Import/Export → Single initiative → 'Add as new' (or 'Update' when the spec carried an existing id or the name matches) → Confirm. sourceMode/language are recorded in the file (defaulting to the context's); whether the app keeps EU-AI-Act fields depends on the organisation's AI-Act module switch.
load_portfolio3 of 3 parameters describedLoads the organisation's FULL BACKUP (BICon app: Import/Export → Backup → Export, a bicon-portfolio-backup-YYYY-MM-DD.json) for analysis and returns a portfolioId plus a summary: counts by status, business unit and driver, the skills, capabilities, saved portfolios and snapshots, currency, budget cap, and NIS2 (coverage, the measure keys and the incident register's counts) while that module is on. Two sources: with LIVE ACCESS set up (the user entered a personal read-only token in the Composer's settings) call it WITHOUT arguments and it reads the portfolio from the app now (`source: "live"`; a read is reused for 5 minutes, `refresh: true` reads again); otherwise pass the backup file's full local `path` (ask the user where it is, often Downloads), or inline `backup` JSON only for small files. If a call without arguments says no source is set up, ask the user for the backup file. Read-only either way: nothing is written, author fields are removed on load. Call once, then pass `portfolio: "<portfolioId>"` to the other analysis tools. The data is as of `exportedAt` in the summary (the read time when live).
query_initiatives6 of 6 parameters describedFilters the loaded portfolio's initiatives (status, business unit, category, driver, tags, saved portfolio, capability, skill, score ranges, overdue milestones or follow-ups, severe risks, quality gaps, NIS2 measures treated) and returns chosen columns per initiative, sorted, plus aggregates over the whole scope (count, budget sum, mean scores, count by status). Columns include the four dimension scores, composite, quadrant, priority bucket, NPV, risks, milestones, follow-ups, quality gaps, last status report, capabilities, the NIS2 measures it treats, skills and dependencies.
portfolio_readings4 of 5 parameters describedComputes portfolio readings with the app's own functions, optionally for a filtered scope: kpis (Steering KPIs), concentration (bars per business unit, category, vendor dependency, driver; HHI for business unit, category and driver, the single-vendor share for vendor dependency), operatingModel (the seven readings), capabilityImpact (domains, top changes, gaps), risks (heat maps current and residual, top risks, unmitigated severe risks), signals (early warnings not yet in the register), boardActions (the Board Actions digest, always the whole portfolio, NIS2 kinds included while that module is on). Board Action kinds and their params are raw values; explain them in words.
rank_initiatives11 of 13 parameters describedRuns the Prioritisation ranking and cut line exactly as the app does, at the organisation's baseline or with a what-if: another budget cap or budget field, a trade-off percent, skill FTE changes, promoted or excluded initiatives, queue statuses, funding regulatory work first or not. Returns funded and parked initiatives in rank order with their bucket and why each parked one is parked, the totals, the must-do block and skill utilisation. Compare two calls to show what a change does.
initiative_detail2 of 2 parameters describedOne initiative in full from the loaded portfolio, by id, externalId or name: every column of query_initiatives plus description, sub-scores, economics, milestones, risks, follow-ups, quality factors, recent status reports and decisions, capability impacts and the initiatives that depend on it.
compare_snapshots6 of 6 parameters describedCompares the portfolio between a snapshot and now (the backup's export), or between two snapshots: the four Steering KPIs with direction and whether each improved, counts by status, budget sum, initiatives added, left (retired, archived, deleted) or changed (status, scores beyond minScoreChange, budget, driver, business unit; largest change first), and how the risk register moved (rose, raised, occurred, closed). Initiatives match by id, else by a unique name.
board_slices4 of 4 parameters describedThe raw data of the Board Memo's chapters, from the same functions the memo and the board pack use: KPIs since the baseline snapshot, capacity (cut line totals, parked by reason, the must-do block), milestones (missed and due in the next 90 days), risks (heat map, top severe, issues and rises since the baseline), quality gaps (top 10, per factor), capability impact (domains, top changes, uncovered gaps) and NIS2 (organisation level while the module is on: coverage, gaps with the initiatives treating them, the management body's approval and training, the incident register: last 12 months, significant, reported on time so far, open of any date, reports overdue now). Use it to draft a memo section, a committee note or slides; state the snapshot and dates the numbers stand on.
skill_allocation9 of 9 parameters describedPer skill of the roster (or the ones named): the FTE cap against org-wide pipeline demand, run FTE of systems in production and the baseline cut line's funded use; every initiative drawing on it (FTE, build or run, funded or parked and why: budget, a skill cap, a dependency, excluded); the Roadmap's monthly demand (run teams only with includeRunTeams, as the page's switch) with the months over cap, the peak and who makes it up; and with skillFteDeltas or excludedIds, what that what-if frees or parks in the cut line.
capability_allocation7 of 7 parameters describedPer capability of the map (or the ones named, or one domain): current, projected and target maturity, the gap, coverage, concentration and attributed spend, from the Capabilities page's own rules; every initiative linked to it (status, kind, the level it brings, planned quarter, spend, and its place in the baseline cut line: funded or parked and why), with atRisk when the projection needs parked pipeline work; the maturity path by quarter (the Timeline tab); and with excludedIds or budgetCap, which capabilities fall back, which gaps open and which initiatives are taken out (funded in the baseline but not in the what-if, or excluded).
get_analysis_template2 of 2 parameters describedReturns the recipe of a ready-made portfolio analysis: which analysis tools to call with which inputs, what to report, and the rules (quote the tools' figures, name the export date). Follow it step by step. The same recipes are offered as prompts and as load_portfolio's nextSteps. Keys: board_briefing (Board briefing on the portfolio); budget_what_if (What if the budget changes); skill_bottlenecks (Skill bottlenecks and what frees them); capability_gaps (Capability gaps and who closes them); risk_review (Risk and delivery review); since_snapshot (What changed since the last snapshot); initiative_brief (One initiative, one page).
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.