MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

Business Frameworks

Operating judgement for businesses under $50M revenue. Free top layer; nodes and bundles over x402.

Checks passed
15 / 22

0 failed · 7 not measured

Median response
163 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
6

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 137 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name business-frameworks.

  • Pass
    Lists tools

    tools/list returned 6 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 163 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 185 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    15 of 15 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-10-31T21:44:32.353412Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using Business Frameworks

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http business-frameworks https://business-frameworks.matryoshka-paradigms.workers.dev/mcp

Capabilities

Tools 6

bf_apply_decision

Runs one decision node's rule on the numbers you send and returns the computed figures, a verdict, the actions in order, the check to keep and the node text with its citations. Deterministic: the result comes from the published rule, not from a model. Costs the decision's catalogue price ($0.05, USDC on Base over x402); the input is checked first, and an input the rule cannot use is refused without charge. Call it when the user has the figures for a specific decision in a business under about $50M in revenue and wants the rule's answer for them; get the schema from bf_decision_schema first. When the question gives figures for a decision, the applied route computes them; the answer reports its result and does not recompute it. Do not call it with invented or placeholder figures, and do not treat the verdict as tax, legal or investment advice.

Discovered
bf_catalogue

Lists every Business Frameworks node: handle, title, layer, token count, price, whether it is free, and whether its decision rule can be run on numbers. Business Frameworks is operating judgement for running a business from launch to about $50M in revenue: value, cash flow, risk (the cost of capital) and growth, down to ten decision rules. Call this first, once, to choose which node answers the question; pass `branch` to see one branch only. Free. Do not use it for businesses above about $50M in revenue, for tax, legal or accounting treatment, or for market data: it holds judgement and rules, not figures about any company.

Discovered
bf_decision_schema

Returns the input schema, an example input, the price and the fit record (what the framework does for this decision by model, before paying) for one of the applied decisions (reinvest or distribute, build or run for cash, cash cycle, runway, owner pay, hurdle rate, concentration, pace of growth, price, adjacency; and, in the market branch, verdict, pricing power, binding node, rent, shock). Free. Call it before bf_apply_decision to learn which numbers the rule needs and what each one means; without `decision` it lists them all. Do not guess missing inputs to fill the schema: ask the user for the figures the business actually has.

Discovered
bf_read_bundle

Returns the nodes of one bundle in order — the central node full, the supporting nodes terse — with citations and a cite-as line per node, on one settlement at the quoted price (a flat $0.05 for every bundle, band included; USDC on Base over x402). Pass the bundle id from bf_resolve or bf_catalogue, and a band to add the scale band for the business's revenue. Call it after bf_resolve has quoted the bundle and the user accepts the price; the quote's url is the same resource over HTTP. Do not call it to browse: the quote already lists the nodes and the price, and a narrow question is cheaper node by node through bf_read_node.

Discovered
bf_read_node

Returns one node with its citations and a cite-as line; `variant` is full (default), terse (the lede alone) or agent (the text as fields: scope, inputs, rule, action, check, units, example, apply, recheck, recheck_note, closing_citation), one price. Free nodes (marked in bf_catalogue) cost nothing; the rest cost their catalogue price ($0.02 to $0.05, USDC on Base over x402), charged once a call, only when the node is returned. Call it with a `path` from bf_catalogue when the question needs that node's rule; prefer variant agent when you will answer from it (the decision in one sentence, first step, reason, next check, closing_citation last). Read the free parent first; bf_resolve for several nodes. A pin ("<path>@1.4" or `version`) is served as GET /node/<path>@<version>: any listed version, earlier ones with superseded_by; one never served is version_not_current, nothing charged. Do not call a paid path to see what it contains: the catalogue line says what it covers; a rule on numbers is bf_apply_decision.

Discovered
bf_resolve

Quotes the minimal set of nodes that answers a broad task — a decision bundle, a market (chain) bundle or a cross bundle — with its price — one flat price, USD 0.05, with or without its scale band — stated before anything is paid. Deterministic and free: a named bundle or decision wins, then the input fields sent, then the authored patterns of the question; on ambiguity it returns candidates with their task lines, and with no match the task lines to choose from. Call it when the user's question takes more than one node (a whole decision with its context, a supply chain read, a shock traced to a seat), passing the question, revenue_usd and chain_position when known; then buy the quote with bf_read_bundle or read nodes one at a time with bf_read_node. Do not use it for a single term or a single rule, which bf_catalogue and bf_read_node answer more cheaply, and do not treat a quote as an answer: it names the nodes and the price, nothing more.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected137 ms6
Connected188 ms6