此 MCP 可以做什么
Shares anonymized tool-failure reports, recovery recommendations, and success outcomes to help agents handle failed calls.
功能
工具
4
工具
check_tool_failure
Check what the network knows about a tool failure
Use FailEcho when another tool fails, before retrying blindly. Call this BEFORE retrying a failed tool, API or MCP call. Returns what other agents saw for this exact failure -- status (HEALTHY/DEGRADED/MAJOR/INSUFFICIENT_DATA), counts, the recovery actions that worked with success rates, and one `recommendation` (or `skip` when nothing tried recently has worked; null when evidence is thin -- a real answer). Works on your own history before anyone else joins. Free, anonymous, stores nothing, never rate limited.
只读
幂等
输入模式
{'type': 'object', 'required': ['service', 'operation'], 'properties': {'service': {'type': 'string', 'maxLength': 128, 'description': "The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias."}, 'verbose': {'type': 'boolean', 'default': False, 'description': 'Full record (timestamps, rates, effective counts, every action). Default: the compact answer.'}, 'version': {'type': 'string', 'maxLength': 64, 'description': 'Service/tool version, if known.'}, 'operation': {'type': 'string', 'maxLength': 128, 'description': "The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'."}, 'error_code': {'type': 'string', 'maxLength': 32, 'description': "Code, e.g. '422', 'ECONNRESET'."}, 'error_type': {'type': 'string', 'maxLength': 64, 'description': "Failure class, e.g. 'validation_error', 'timeout', 'rate_limit', 'auth_error'."}, 'reporter_id': {'type': 'string', 'maxLength': 200, 'description': 'Optional stable agent id; hashed, never stored raw. Lets from_other_agents be answered.'}, 'schema_hash': {'type': 'string', 'maxLength': 64, 'description': "Short hash of the tool schema you used (separates 'API broke' from 'schema stale')."}, 'error_message': {'type': 'string', 'maxLength': 2000, 'description': 'The error text only; normalized server-side, not stored by this call.'}}}
输出模式
{'type': 'object', 'title': 'check_tool_failureDictOutput', 'additionalProperties': True}
report_recovery_outcome
Report whether a recovery action worked
After acting on a failure -- retry, wait, refresh_schema, reconnect, use_fallback, reauthenticate -- report whether it worked. Every recommendation others get is built from these. Pass the fingerprint from check_tool_failure or report_tool_failure; one outcome per attempt.
输入模式
{'type': 'object', 'required': ['fingerprint', 'action', 'successful'], 'properties': {'action': {'type': 'string', 'maxLength': 64, 'description': "What you tried, e.g. 'refresh_schema' ([a-z0-9_.-])."}, 'successful': {'type': 'boolean', 'description': 'True when the action resolved the failure.'}, 'fingerprint': {'type': 'string', 'pattern': '^[0-9a-f]{32}$', 'description': 'From check_tool_failure or report_tool_failure (32 hex chars).'}, 'reporter_id': {'type': 'string', 'maxLength': 200, 'description': 'Optional stable agent id; hashed, never stored raw.'}}}
输出模式
{'type': 'object', 'title': 'report_recovery_outcomeDictOutput', 'additionalProperties': True}
report_tool_failure
Report a failed tool call to the network
Report a failed tool/API/MCP call so others can recognise it; call after a failure, alongside check_tool_failure.
PRIVACY: this is a shared network. Send failure metadata only -- never prompts, tool arguments, tool results, request or response bodies, headers, cookies, API keys, tokens, emails or user content. Error text is normalized server-side and the raw string discarded. A stable reporter_id (hashed, never stored raw) makes you one reporter instead of anonymous noise. Writes are rate limited per client.
输入模式
{'type': 'object', 'required': ['service', 'operation'], 'properties': {'service': {'type': 'string', 'maxLength': 128, 'description': "The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias."}, 'version': {'type': 'string', 'maxLength': 64, 'description': 'Version of the service/tool.'}, 'operation': {'type': 'string', 'maxLength': 128, 'description': "The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'."}, 'error_code': {'type': 'string', 'maxLength': 32, 'description': "Protocol/vendor code, e.g. '422'."}, 'error_type': {'type': 'string', 'maxLength': 64, 'description': "Short failure class, e.g. 'validation_error'."}, 'latency_ms': {'type': 'integer', 'minimum': 0, 'description': 'Observed call latency in milliseconds.'}, 'reporter_id': {'type': 'string', 'maxLength': 200, 'description': 'Optional stable identifier for your agent. Salted and hashed on arrival; never stored raw.'}, 'schema_hash': {'type': 'string', 'maxLength': 64, 'description': 'Short hash of the tool schema used.'}, 'error_message': {'type': 'string', 'maxLength': 2000, 'description': 'Error text. Normalized before storage; no secrets please.'}}}
输出模式
{'type': 'object', 'title': 'report_tool_failureDictOutput', 'additionalProperties': True}
report_tool_success
Report a successful tool call to the network
Report that a call SUCCEEDED. Failure rates are failures over all calls; a network that only hears failures cannot tell broken from busy. No error data -- service, operation, version, latency.
输入模式
{'type': 'object', 'required': ['service', 'operation'], 'properties': {'service': {'type': 'string', 'maxLength': 128, 'description': "The MCP server's own name (serverInfo.name) or the API host, e.g. 'api.github.com'. Not your client's local alias."}, 'version': {'type': 'string', 'maxLength': 64, 'description': 'Version of the service/tool.'}, 'operation': {'type': 'string', 'maxLength': 128, 'description': "The tool or endpoint as the server names it, e.g. 'create_issue', not 'mcp__github__create_issue'."}, 'latency_ms': {'type': 'integer', 'minimum': 0, 'description': 'Observed call latency in milliseconds.'}, 'reporter_id': {'type': 'string', 'maxLength': 200, 'description': 'Optional stable agent id; hashed, never stored raw.'}, 'schema_hash': {'type': 'string', 'maxLength': 64, 'description': 'Short hash of the tool schema used.'}}}
输出模式
{'type': 'object', 'title': 'report_tool_successDictOutput', 'additionalProperties': True}
历史
近期工具变更
已更改
report_recovery_outcome
2026年9月27日 02:52
已更改
report_tool_success
2026年9月27日 02:52
已更改
report_tool_failure
2026年9月27日 02:52
已更改
check_tool_failure
2026年9月27日 02:52
已更改
report_recovery_outcome
2026年9月21日 02:59
已更改
report_tool_success
2026年9月21日 02:59
已更改
report_tool_failure
2026年9月21日 02:59
已更改
check_tool_failure
2026年9月21日 02:59
已更改
report_recovery_outcome
2026年9月19日 02:51
已更改
report_tool_success
2026年9月19日 02:51
已更改
report_tool_failure
2026年9月19日 02:51
已更改
check_tool_failure
2026年9月19日 02:51
已添加
report_recovery_outcome
2026年9月17日 12:34
已添加
report_tool_success
2026年9月17日 12:34
已添加
report_tool_failure
2026年9月17日 12:34
已添加
check_tool_failure
2026年9月17日 12:34
发现
类似的 MCP 服务器
Delx Commerce — Pay-per-Result APIs for Agents
io.github.davidmosiah/delx-mcp-a2a
Provides pay-per-result APIs and agent protocol tools for continuity, multi-agent coordination, document OCR, and crypto-related …
SAP MCP Server
ai.oobeprotocol.sap.mcp/sap-mcp
Provides an MCP gateway connecting SAP-related tools with Solana, DeFi, decentralized identity, and x402 payments.
TheProtocol — Sovereign AI Agent Platform
cloud.theprotocol/registry
Manages sovereign AI agents, identities, contracts, payments, governance, exchanges, and cross-frame token transfers.
AIMEAT
io.aimeat/aimeat
Provides a self-hosted agent operating system with agent work delegation, access controls, federation, hooks, SSO, security admin…
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
GPT55 Model Gateway
xyz.558686.gpt55/token-gateway
Acts as a remote model gateway exposing GPT chat, coding and review services, lightweight text utilities, and prepaid or x402-bas…
Rokha
ai.rokha/rokha
Provides access to an agent-skill and MCP server registry, skill inspection and composition tools, OAuth connections, and agent a…
Japan Public Ledgers MCP
com.mcp-revenue-empire/japan-public-ledgers
Provides agent identity, memory, audit, trust, proxy, temporary email, webhook, CAPTCHA, and alerting capabilities alongside publ…