Signal-first Bitcoin intelligence over MCP. Surfaces leading, non-price indicators — sovereign reserve adoption, Bitcoin/crypto-infra hiring velocity, and network hashrate trend — each with a 0–100 strength, a direction (tailwind/headwind/neutral), a one-line rationale, and primary sources. Tools: scan_signals, get_hiring_signal, get_sovereign_reserves, get_network_signal, get_daily_brew. Resource: coinbucha://methodology. Information, not financial advice.
Scored across 8 tools
Most tools have clearly distinct resource/action targets, and descriptions explicitly distinguish specific signals from aggregate feeds. The main overlap is between get_daily_brew and scan_signals, which both return cross-signal summaries, and get_signal_history can query the same signals as the specific get_*_signal tools; these are differentiated by format and time scope but could still be confused.
Naming is predominantly consistent snake_case with a get_<resource> pattern for seven tools. scan_signals breaks the get_ verb convention, and get_daily_brew is a stylized name, but overall the pattern remains readable and predictable.
Eight tools is well within the appropriate range for a focused Bitcoin-signals API. Each tool covers a distinct signal or aggregate view, and the retired get_etf_flows is retained deliberately for compatibility rather than adding real surface.
The surface covers the four advertised signal types (sovereign adoption, hiring velocity, corporate treasury, network hashrate) plus aggregate scan, daily digest, and history. The retired ETF-flow tool represents a deliberate data-availability gap, and there is no generic signal-type listing, but core observational coverage is strong.
The day's machine-readable digest of the whole signal set — the CoinBucha Daily Brew. Takes no arguments. Returns { date, btc_price_usd, headline, signals_summary[] }, one summary line per signal with its strength, direction and one-line why. Example: {}. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, and the description adds valuable context by specifying the exact return structure (date, btc_price_usd, headline, signals_summary[]) and explaining each signal line. The disclaimer 'Information, not financial advice' also clarifies the tool's nature. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, immediately stating the tool's purpose. It includes a compact example of the return structure and a disclaimer, all within three sentences. Every sentence contributes to understanding, with no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description fully specifies the response format and content, ensuring the agent knows what to expect. It also covers the tool's input (none), return fields, and a caveat. Combined with strong annotations for safety, the description is complete for this simple read-only tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and the schema confirms this with 100% coverage. The description states 'Takes no arguments,' which is redundant but harmless. Per the baseline for 0 params, a score of 4 is appropriate since no parameter meaning needs to be added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool as providing 'The day's machine-readable digest of the whole signal set,' distinguishing it from siblings that focus on individual signals. The verb 'returns' and specifics (date, btc_price, headline, signals_summary) make its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for a broad overview via 'whole signal set' and lists what the digest contains, but it does not explicitly state when to choose this over sibling tools like scan_signals or get_hiring_signal. No exclusions or alternative recommendations are provided, so guidance is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
RETIRED: this tool is no longer advertised and serves no flow figures. No spot-Bitcoin-ETF flow source is available that is both key-free and permitted to redistribute, so CoinBucha never had a licensed figure to serve here. It remains callable so existing integrations do not break: it takes no arguments and returns { available: false, status, as_of, date_basis, unit, note, disclaimer }, stating the absence explicitly. Read that absence as absent — never as a zero flow. For live signals use scan_signals, get_sovereign_reserves, get_treasury_holdings, get_hiring_signal, get_network_signal or get_daily_brew. Example: {}. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnly and idempotent hints. The description goes beyond this by disclosing that the tool returns a fixed structure with explicit fields, that it is callable but inert, and crucially warns against misinterpreting the absence as a zero flow. This is valuable behavioral context not inferable from annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Although the description is longer than typical, every sentence serves a purpose: retirement status, rationale, compatibility note, return structure, warning, alternative routing, example, and disclaimer. It is front-loaded with 'RETIRED' and structured logically, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite being a retired tool with no output schema, the description fully specifies the return object fields, explains the tool's history and current behavior, provides alternatives, and includes a usage caution. An agent has complete information to handle this tool correctly, including when to avoid it.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, so the schema already covers everything. The description redundantly states 'takes no arguments', but this adds no new semantics. Per the guideline for 0 params, baseline is 4; no further explanation is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is RETIRED and serves no flow figures, explicitly defining its purpose as returning an absence status rather than data. It distinguishes itself from siblings by naming live alternatives such as scan_signals and get_sovereign_reserves, making its role unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly instructs when to use this tool (for compatibility of existing integrations) and when not to (for live signals, pointing to specific sibling tools). It also provides a critical behavioral note — to read absence as absence, not zero — which directly guides agent interpretation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Hiring velocity across tracked Bitcoin and crypto-infrastructure employers, counted from their live ATS boards. Returns { as_of, companies[], note, why, disclaimer }; each company carries company, ticker, category, ats, careers_url, open_roles, open_roles_30d_ago, open_roles_90d_ago and the derived delta_30d, delta_90d and pct_30d. Example: {"company": "coinbase"} for one employer, or {} for every employer tracked. When a company filter matches no tracked employer the response adds coverage_note and tracked_count, saying that the name is outside the tracked set — a limit of coverage, not a finding about whether that company is hiring. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| company | No | Case-insensitive company filter |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the annotations by disclosing the full response shape (as_of, companies[], note, why, disclaimer), the per-company fields including derived deltas, and the special coverage_note/tracked_count behavior when no tracked employer matches. It also includes the financial disclaimer.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences pack purpose, response format, example, edge case, and disclaimer. Each sentence adds value, front-loading the core purpose. No fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema exists, the description thoroughly covers the return structure and edge cases, making it complete for an agent to understand what will be returned and how to interpret the data. The note about coverage limits is particularly valuable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already covers the single parameter well with 'Case-insensitive company filter'. The description adds a concrete example using {"company": "coinbase"} and clarifies the empty-filter behavior, providing practical usage guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description specifies the exact resource ('tracked Bitcoin and crypto-infrastructure employers') and the measurable ('hiring velocity'), distinguishing it clearly from sibling tools like etf_flows or treasury_holdings. The verb 'counted from their live ATS boards' adds precision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context on when to use (for hiring velocity data) and how to filter via the optional company parameter, including the no-match behavior. It does not explicitly name alternative tools or state when not to use, but the context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Bitcoin network hashrate level and trend. Takes no arguments. Returns { as_of, hashrate_eh (exahashes per second), pct_30d, pct_90d, why, disclaimer }. Example: {}. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond the readOnlyHint and idempotentHint annotations by specifying the output fields (as_of, hashrate_eh, pct_30d, pct_90d, why, disclaimer) and includes a disclaimer ('Information, not financial advice'). This discloses behavioral aspects like the data returned and its nature, without contradicting the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, with the purpose front-loaded in the first sentence. The second sentence efficiently covers arguments, return fields, and a disclaimer. Every sentence earns its place, and the 'Example: {}' is a compact way to illustrate usage.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no arguments, no output schema), the description provides a comprehensive overview by listing all returned fields and including a caution. It lacks detailed explanations of 'why' or 'disclaimer', but for a read-only informational endpoint, it is sufficiently complete for an agent to invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4 per the rubric. The description explicitly states 'Takes no arguments', which matches the empty input schema. While it adds no parameter-specific meaning, the zero-parameter case is handled clearly and accurately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool provides 'Bitcoin network hashrate level and trend', a specific resource and function. It differentiates from sibling tools like get_etf_flows or get_sovereign_reserves by topic, making it unambiguous which tool to use for hashrate data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains that the tool 'takes no arguments' and returns a specific structure, but it does not explicitly state when to use it versus alternatives. Usage is implied from the title and topic, but no exclusions or alternative tool references are provided, so guidance is limited to context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Dated strength history for one CoinBucha signal, newest first. Returns { as_of, signal_type, title, unit, count, points[], truncated, available_points, tier_window_points, freshness, why, disclaimer, cite }, where each point carries date, signal_strength (0-100) and direction (tailwind | headwind | neutral). Example: {"signal_type": "network_hashrate", "days": 30}. signal_type is one of sovereign_adoption, hiring_velocity, corporate_treasury, network_hashrate. Anonymous and free-tier callers receive the most recent points only and are told so by truncated and available_points; no figure is ever altered or interpolated to fit a window. Observational data; information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | How many of the most recent dated points to return (1-90) | |
| signal_type | Yes | Which signal's history to return |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly/idempotent safety. The description adds real behavioral value beyond them: the truncation policy for anonymous and free-tier callers, the no-alteration/no-interpolation guarantee, and the freshness/truncated/available_points metadata. It stops short of stating rate limits or auth requirements explicitly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loads the purpose and return shape, then example, then constraints. It is information-dense but the long inline return-field enumeration and the meta-justification about not changing figures are slightly verbose; still, every clause carries usable signal.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, scope, return field names, valid enum values, example call, and access-tier truncation behavior. With no output schema, the inline field list is appropriate; the only gap is explicit routing to sibling tools for current readings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3, but the description adds meaning: it enumerates the valid signal_type values and gives a concrete example call with days=30, plus explains the returned string('date, signal_strength 0-100, direction'). This enriches the semantics of both parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Dated strength history for one CoinBucha signal'), specifies a single signal scope, and notes ordering ('newest first'). An agent can distinguish it from sibling scan_signals or the per-signal getters that return current readings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Clear context (history for one named signal) and it indirectly signals the alternative scanning/current tools by its naming, but it never explicitly names a sibling or states when-not to use this tool (e.g., versus scan_signals for current readings). Strong context without explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Nation-state Bitcoin holdings, ranked largest first. Returns { as_of, btc_price_usd, count, sovereigns[], disclaimer }; each row carries country_name, country_code, holdings_btc, status, tier (1 = largest holders), framework, sources[], its own as_of, and source_quality (primary = confirmed against the state's own publication; secondary = reported, not confirmed at source — derived from that row's sources[]). Filter by country name or ISO code, or by tier. Example: {"country": "US"} or {"tier": 1} — call with {} for the full ranking. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Holding tier; 1 = largest holders | |
| country | No | Country name or ISO code |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent behavior, and the description adds substantial context: the full return shape, per-row fields, the meaning of source_quality, and the disclaimer. It clarifies that source_quality is derived from each row's sources[], which goes beyond the structured annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but well-structured, front-loading the core purpose and then enumerating output details and usage examples. It is somewhat long due to the rich return field breakdown, but every sentence contributes meaningful information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description fully compensates by enumerating the top-level and per-row fields, explaining tier and source_quality semantics, and giving usage examples. It provides enough context for an agent to invoke the tool and interpret results correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers both parameters with descriptions, so baseline is 3. The description adds value by clarifying filtering semantics ('country name or ISO code'), providing examples for each parameter, and explaining that empty input returns the full ranking — details not present in the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with a specific verb and resource: 'Nation-state Bitcoin holdings, ranked largest first.' It clearly states what the tool returns and the ordering, and the 'Nation-state' qualifier distinguishes it from sibling tools like get_treasury_holdings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit usage patterns: filter by country name or ISO code, filter by tier, and call with {} for the full ranking. It provides concrete examples but does not explicitly mention when not to use this tool or compare it to alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Bitcoin held on the balance sheets of tracked public companies, in aggregate and by largest holder. Takes no arguments. Returns { as_of, total_btc, company_count, total_value_usd, top[], why, disclaimer }, where top[] lists the largest holders as { name, symbol, btc }. Example: {}. Information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnly and idempotent hints. The description adds valuable context by specifying the exact return structure ({ as_of, total_btc, company_count, total_value_usd, top[], why, disclaimer }), clarifying that it covers 'tracked' companies only, and including a 'not financial advice' disclaimer. This goes beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and efficiently structured: it states the purpose, notes the lack of arguments, details the return fields, provides an example, and includes a disclaimer—all in four short sentences with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite lacking an output schema, the description fully defines the return format, including the nested top[] structure. It also includes an example and a disclaimer, making the tool's output and limitations clear for a parameterless operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the description explicitly confirms 'Takes no arguments,' matching the empty input schema. With zero parameters, the baseline is 4, and nothing needs further explanation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's function: reporting Bitcoin held on balance sheets of tracked public companies, both in aggregate and by largest holder. This clearly differentiates it from sibling tools like get_etf_flows or get_sovereign_reserves, which focus on other data domains.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended use case is implied by the description (analyzing corporate bitcoin treasuries), but there is no explicit guidance on when to use this tool versus alternatives, nor any exclusion criteria. It relies on the user to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ranked cross-signal feed of CoinBucha's leading, non-price Bitcoin indicators. Returns { as_of, btc_price_usd, count, signals[], disclaimer }, where each signal carries id, type, title, value, unit, signal_strength (0-100), direction (tailwind | headwind | neutral), a one-line why, sources[] and its own as_of. Optional filters narrow by strength, direction or signal type. Example: {"min_strength": 70, "direction": "tailwind"} — call with {} for the full ranked list. Observational data; information, not financial advice.
| Name | Required | Description | Default |
|---|---|---|---|
| direction | No | Keep only signals carrying this direction label | |
| min_strength | No | Only signals with strength >= this | |
| signal_types | No | e.g. ['sovereign_adoption','hiring_velocity'] |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only and idempotent behavior. The description adds valuable behavioral context: it explicitly labels the data as observational and disclaims financial advice, and details the return structure (top-level keys and per-signal fields). This goes beyond what annotations convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and well-structured: purpose, return schema, filter options, an example, and a caveat are all presented in three dense sentences with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the lack of an output schema, the description thoroughly enumerates the response fields and per-signal attributes, explains the optional filters, and provides an example. This is complete enough for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions for all three parameters. The description enhances this by providing a concrete invocation example and clarifying that an empty object yields the full ranked list, which aids real-world usage beyond the schema's static descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool as a 'Ranked cross-signal feed of CoinBucha's leading, non-price Bitcoin indicators.' This specific verb-resource pair distinguishes it from sibling tools that target individual data streams such as ETF flows or network signals.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use for a cross-signal overview and provides filter examples, but it does not explicitly state when to use this tool versus the sibling getters. No exclusions or alternative-tool references are given, so guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_signal_historyget_daily_brew1 field changedInput schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"get_etf_flows1 field changedInput schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"get_network_signal1 field changedInput schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"get_sovereign_reserves1 field changedInput schema / properties / tier / descriptionAdded value: +"Holding tier; 1 = largest holders"get_treasury_holdings1 field changedInput schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"scan_signals1 field changedInput schema / properties / direction / descriptionAdded value: +"Keep only signals carrying this direction label"get_etf_flowsget_treasury_holdingsget_daily_brewget_hiring_signalget_network_signalget_sovereign_reservesscan_signals
Add one secure layer between your agents and this server.