MCP tool reference · #266 of 563 by publishers
call_tool
Exposed by 13 servers from 11 publishers, read from the live servers by the Serverdex check; 92.3% of them take a name parameter; the most-starred is Hermoso: AI Ad Generator (9 stars).
call_tool(name: string, arguments?: object, …)Parameters
share = % of the 13 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| name | string | 92.3% | 100% | The tool's name from find_tool, for example weather_forecast |
| arguments | object | 76.9% | 0% | Arguments for the tool, matching its input schema; {} when it needs none |
| args | object | 15.4% | 0% | the tool's arguments as an object, exactly as its own schema takes them |
| context | string | 15.4% | 0% | optional: the user's underlying goal in one short sentence, for analytics only (no names, contact details or URLs); every tool also accepts it directly |
| max_price | — | 15.4% | 0% | Only for a tool that costs more than $0.10 a call: the most this call may cost, for example "$1.00". Leave it out for every other tool |
| revision | string | 15.4% | 0% | the revision find_tools gave for this tool; a changed tool is refused unrun, with its current params |
| append | boolean | 7.7% | 0% | Add rows to an existing store_as table instead of replacing it. |
| detail | — | 7.7% | 0% | 'brief' (the default): values, units, citation, caveats and limits, long row lists as CSV. 'full': every field and the full provenance. |
| fetch_all | boolean | 7.7% | 0% | Follow every page into store_as in this one call. |
| params | object | 7.7% | 0% | Endpoint params. |
| store_as | string | 7.7% | 0% | Table name: store rows in SQLite, return only a summary. Read with query_data. |
| tool_id | string | 7.7% | 100% | Catalog tool id from search_tools, e.g. 'openrouter.chat', 'perplexity.answer', 'sec.edgar_search', 'elevenlabs.tts' |
Source: the input schema each server returns for call_tool, aggregated over the 13 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with call_tool
13 of 13 · 11 publishers · 13 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes call_tool |
|---|---|---|---|---|---|---|
| 1 | Hermoso: AI Ad Generatorhermoso-ai · Developer Tools | hermoso-ai | Developer Tools | 9 | yes | Run a Hermoso tool that is not in this session's starting list (paid campaigns, analytics, channel admin and more), using the exact `name` and `args` that find_tools returned. Use find_tools first. It runs that one tool on this Hermoso account, and the tool's own rules still apply: a spend or a delete still asks for confirm. Use it on hosts that keep the tool list they fetched at connect time (cla |
| 2 | Hermosohermoso-ai · Other | hermoso-ai | Other | 8 | yes | Run a Hermoso tool that is not in this session's starting list (paid campaigns, analytics, channel admin and more), using the exact `name` and `args` that find_tools returned. Use find_tools first. It runs that one tool on this Hermoso account, and the tool's own rules still apply: a spend or a delete still asks for confirm. Use it on hosts that keep the tool list they fetched at connect time (cla |
| 3 | MapleStats MCPdsanchezp18 · Data & Analytics | dsanchezp18 | Data & Analytics | 7 | yes | Run one Canadian data tool (Statistics Canada, Bank of Canada, CMHC, provincial and city sources) found through search_tools or plan_query. Use for: executing a tool by exact name with arguments that match the arguments search_tools returned for it. Data tools read public sources (StatCan, Bank of Canada, open-data portals). reproduce_workbook can save an Excel file on a local stdio server; hoste |
| 4 | Zooza MCP Serverzooza-dev · Maps, Travel & Weather | zooza-dev | Maps, Travel & Weather | 6 | yes | Runs a Zooza tool by name. Use it for every Zooza tool that is NOT in your tool list — these exist and work; never send the user to another app because a Zooza tool isn't listed. Call get_tool_schema(name) first for the arguments. Write tools behave exactly as when called directly: the first call previews and returns a token, the second (token + confirmed:true) applies. Tools reachable this way: - |
| 5 | TickerDBtickerdb · Finance | tickerdb | Finance | 5 | yes | Run an endpoint found with search_tools: its name plus a params object. store_as, append and fetch_all work as on the other data tools. |
| 6 | AINumbers Fintech Intelligence Suitepostoaklabs · Finance | postoaklabs | Finance | 3 | yes | Runs ONE read-only AINumbers tool that is not in your tool list. tools/list is paginated (13 pages, 722 tools) and many hosts read only the first page; this is the door to the rest. Pass { name: "<exact mcp_name>", arguments: { ... } } — the target's own inputSchema is validated and its result is returned verbatim, including execution_hash, so a dispatched call and a direct call are byte-identical |
| 7 | Agent Data Tools: Compact (find, describe, run)nutshell2000 · Search & Web | nutshell2000 | Search & Web | 1 | yes | Run one of this service's tools by name. Costs that tool's own price per successful call (most $0.01; tool_details and find_tool show it); a failed call costs nothing, and tools marked inFreeCalls (tools that only compute or look up public data; not AI, speech, transcription, images, rendering, search or resold data) run free while the caller has free calls left. Pass the tool's inputs as "argumen |
| 8 | Agent Data Toolsnutshell2000 · Crypto & Web3 | nutshell2000 | Crypto & Web3 | 1 | yes | Run one of this service's tools by name. Costs that tool's own price per successful call (most $0.01; describe_tool and find_tool show it); a failed call costs nothing, and tools marked inFreeCalls (tools that only compute or look up public data; not AI, speech, transcription, images, rendering, search or resold data) run free while the caller has free calls left. Pass the tool's inputs as "argume |
| 9 | Troothtroothllc · Other | troothllc | Other | 1 | yes | Runs one read-only tool by its name with its arguments, exactly as calling it directly does: the same sign-in, scopes and limits. Use it for a tool search_tools or enable_toolset named that your client does not list. A tool that changes something runs through call_write_tool. |
| 10 | Litescrapelitescrape · Search & Web | litescrape | Search & Web | 1 | yes | Run a Litescrape tool found with find_tools. Pass its name and arguments matching its input schema; arguments may also take result_groups to keep only some top-level groups. |
| 11 | Helvehelve-dev · APIs & Integrations | helve-dev | APIs & Integrations | — | yes | Invoke any tool in Helve's catalog by tool_id with tool-specific arguments (discover tool_ids and schemas first via search_tools). Metered per call against your single Helve balance; failed upstream calls debit $0. |
| 12 | TrueScrapetruescrape · Other | truescrape | Other | — | yes | Run a data tool by name, loaded or not, at that tool's own price. Monitor and watch tools are called directly. |
| 13 | Final POS – Custom POS Builderfinal-commerce · Developer Tools | final-commerce | Developer Tools | — | yes | Run a read-only tool from any allowed pack by its full name (for example hub_find_low_stock) without it being listed. Only tools that read are accepted; tools that change data run through call_write_tool. Arguments follow that tool's own input schema, which find_tools returns. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.