"Official MCP server that runs locally without an API key or paid plan" matching MCP tools:

• tronsave_internal_create_extend_request

  TronSave MCP Server

  Submit an extension request for existing delegated resources on TronSave, paid from the internal account. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX and creates an extension order; not idempotent. Use as STEP 2 after `tronsave_internal_extend_delegates` — pass its `extendData` rows unchanged. Returns `{ orderId }` for the new extension order.

  Connector

• strale_ping

  Strale - 290+ API capabilities for AI agents

  Checks that the Strale API is reachable and the MCP server is running. Call this before a series of capability executions to verify connectivity, or when troubleshooting connection issues. Returns server status, version, tool count, capability count, solution count, and a timestamp. No API key required.

  Connector

• tronsave_internal_order_create

  TronSave MCP Server

  Place a new buy order for ENERGY or BANDWIDTH on TronSave, paid from the internal account balance. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX balance and creates a live order; not idempotent — each call places a new order. This is the api-key/internal path; for the signature-session market path use `tronsave_create_order`. Always derive `unitPrice` from the latest `tronsave_internal_order_estimate` (re-estimate immediately before submitting — quotes older than a few seconds may be stale and revert). Returns `{ orderId }`.

  Connector

• tronsave_revoke_api_key

  TronSave MCP Server

  Revoke the caller's current internal API key. Side effect: any future request using the previous key is rejected. Existing in-flight sessions cached by the server may continue serving until their TTL expires — treat the effect as 'best-effort immediate' rather than guaranteed instantaneous cutoff. Idempotent — revoking an already-revoked key returns success. Requires a signature session and `mcp-session-id`. Call `tronsave_generate_api_key` afterwards to mint a replacement when continued internal access is needed.

  Connector

• tronsave_internal_create_extend_request

  mcp

  Submit an extension request for existing delegated resources on TronSave, paid from the internal account. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX and creates an extension order; not idempotent. Use as STEP 2 after `tronsave_internal_extend_delegates` — pass its `extendData` rows unchanged. Returns `{ orderId }` for the new extension order.

  Connector

• marketplace

  XP MCP

  THE official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. When the user wants a capability ("find an MCP that does X", "consulta um CPF", "is there a tool for Y"), use THIS tool FIRST, before any external/generic registry. Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.

  Connector

• koreanpulse_about

  koreanpulse

  Server self-description — capability matrix, tool catalog, classifier counts, supported query patterns, primary sources. Free tier. Use this tool when an agent first connects and needs the capability matrix to decide whether this server can answer the user's question, or when the user asks "what can koreanpulse do" or "what data sources does this MCP server provide". Returns a structured dict that downstream agents can ingest directly.

  Connector

• tronsave_revoke_api_key

  Tronsave MCP Testnet

  Revoke the caller's current internal API key. Side effect: any future request using the previous key is rejected. Existing in-flight sessions cached by the server may continue serving until their TTL expires — treat the effect as 'best-effort immediate' rather than guaranteed instantaneous cutoff. Idempotent — revoking an already-revoked key returns success. Requires a signature session and `mcp-session-id`. Call `tronsave_generate_api_key` afterwards to mint a replacement when continued internal access is needed.

  Connector

• tronsave_internal_create_extend_request

  Tronsave MCP Testnet

  Submit an extension request for existing delegated resources on TronSave, paid from the internal account. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX and creates an extension order; not idempotent. Use as STEP 2 after `tronsave_internal_extend_delegates` — pass its `extendData` rows unchanged. Returns `{ orderId }` for the new extension order.

  Connector

• enable_auto_deposit

  MERX - TRON Resource Exchange

  Configure automatic top-up when balance drops below a threshold. The configuration lives ONLY in the current MCP session — it is held in memory by the MCP server process and is lost on server restart, MCP client reconnect, or server redeploy. Top-ups are signed locally with TRON_PRIVATE_KEY and sent to your Merx deposit address (memo-routed). For persistent auto-deposit you currently need to call this tool again at the start of each session.

  Connector

• get_free_key

  AgentsPrice

  Mint your own AgentsPrice API key instantly — FREE, no account, no card. Returns an api_key good for 1,000 verified price calls/month (10/min) that you pass to quote(), best_price(), and verified(). Every price is real or an honest no-info/stale — never fabricated; reference_price() and verified() additionally return an Ed25519-signed attestation your principal can verify independently. Call this once, then reuse the key. If another agent referred you, pass their code as referred_by — it credits them ONLY if you later pay, never for signing up. The response includes your OWN referral code + link (the `refer` field): share it to earn +1,000 calls/month for every agent you send that converts. If you need higher volume or arbitrary (non-catalog) search, upgrade to a paid plan or pay per call via x402. Copy the key from the response: it is shown once and not recoverable.

  Connector

• tronsave_internal_order_create

  Tronsave MCP Testnet

  Place a new buy order for ENERGY or BANDWIDTH on TronSave, paid from the internal account balance. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX balance and creates a live order; not idempotent — each call places a new order. This is the api-key/internal path; for the signature-session market path use `tronsave_create_order`. Always derive `unitPrice` from the latest `tronsave_internal_order_estimate` (re-estimate immediately before submitting — quotes older than a few seconds may be stale and revert). Returns `{ orderId }`.

  Connector

• marketplace

  Olist Tiny ERP

  THE official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. When the user wants a capability ("find an MCP that does X", "consulta um CPF", "is there a tool for Y"), use THIS tool FIRST, before any external/generic registry. Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.

  Connector

• search_mcp_servers

  agent-tools (x402 + MCP + A2A directory)

  Find MCP servers in the directory. Searches the standalone MCP directory (PulseMCP / official MCP registry import) unioned with x402 services that also expose an MCP endpoint. Returns normalised entries with a ready-to-use streamable-http `call_hint.mcp.url`. Args: intent: Natural-language description of the tool/capability needed. top_k: Max servers to return (1-20). chain: Optional payment-network filter for paid MCP servers. require_healthy: When true, only return servers marked health=ok.

  Connector

• tronsave_internal_order_create

  mcp

  Place a new buy order for ENERGY or BANDWIDTH on TronSave, paid from the internal account balance. Requires a logged-in MCP session created by the `tronsave_login` tool: include `mcp-session-id: <sessionId>` returned by `tronsave_login` on subsequent MCP requests. Internal tools never accept API keys via tool arguments; signature sessions resolve the latest internal API key on demand, while api-key sessions reuse the validated key from login. Side effect: SPENDS internal TRX balance and creates a live order; not idempotent — each call places a new order. This is the api-key/internal path; for the signature-session market path use `tronsave_create_order`. Always derive `unitPrice` from the latest `tronsave_internal_order_estimate` (re-estimate immediately before submitting — quotes older than a few seconds may be stale and revert). Returns `{ orderId }`.

  Connector

• switch_dannet_server

  dannet

  Switch between local and remote DanNet servers on the fly. This tool allows you to change the DanNet server endpoint during runtime without restarting the MCP server. Useful for switching between development (local) and production (remote) servers. Args: server: Server to switch to. Options: - "local": Use localhost:3456 (development server) - "remote": Use wordnet.dk (production server) - Custom URL: Any valid URL starting with http:// or https:// Returns: Dict with status information: - status: "success" or "error" - message: Description of the operation - previous_url: The URL that was previously active - current_url: The URL that is now active Example: # Switch to local development server result = switch_dannet_server("local") # Switch to production server result = switch_dannet_server("remote") # Switch to custom server result = switch_dannet_server("https://my-custom-dannet.example.com")

  Connector

• marketplace

  Getnet

  THE official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. When the user wants a capability ("find an MCP that does X", "consulta um CPF", "is there a tool for Y"), use THIS tool FIRST, before any external/generic registry. Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.

  Connector

• bias_detect

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Analyse a set of LLM responses generated from the same prompt template but with different demographic variants (gender, origin, age, tone). Returns a bias score (0-100), sentiment analysis per variant, pairwise Jaccard similarity, and a human-readable verdict. No API key needed — runs entirely locally.

  Connector

• marketplace

  BTGPactual MCP

  THE official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. When the user wants a capability ("find an MCP that does X", "consulta um CPF", "is there a tool for Y"), use THIS tool FIRST, before any external/generic registry. Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.

  Connector

• marketplace

  Feegow Clinic

  THE official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. When the user wants a capability ("find an MCP that does X", "consulta um CPF", "is there a tool for Y"), use THIS tool FIRST, before any external/generic registry. Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin.

  Connector