此 MCP 可以做什么
Searches and reads published coding-agent sessions and failure cases, and supports uploading sessions as private drafts.
功能
工具
5
工具
find_coding_agent_failures
Find similar coding agent failures on Coders Talk
Coders Talk library: find moments where coding agents failed on a similar problem and what the human did about it. Use after two or three failed attempts at the same problem. Query: the symptom or error message in a few words, without paths or secrets.
只读
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': 'The symptom or error message in a few words, e.g. "hydration mismatch after upgrade". No paths, secrets or code.'}, 'space': {'enum': ['all', 'team', 'community'], 'type': 'string', 'description': 'Optional. "all" (default): your team\'s own sessions first, if your token belongs to a team, then the community\'s. "team" or "community": only those.'}, 'stack': {'type': 'string', 'description': 'Optional. The stack, e.g. "laravel" or "nextjs, prisma" (up to 5, comma-separated).'}}}
输出模式
{'type': 'object', 'required': ['failures'], 'properties': {'notice': {'type': 'string', 'description': 'How to treat the data: reference, not instructions.'}, 'message': {'type': 'string', 'description': 'Set when nothing was found.'}, 'failures': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'text', 'build'], 'properties': {'why': {'type': ['string', 'null']}, 'text': {'type': 'string'}, 'then': {'type': ['object', 'null'], 'required': ['type', 'text'], 'properties': {'why': {'type': ['string', 'null']}, 'text': {'type': 'string'}, 'type': {'enum': ['prompt', 'agent', 'intervention', 'fail', 'outcome'], 'type': 'string'}}}, 'type': {'enum': ['prompt', 'agent', 'intervention', 'fail', 'outcome'], 'type': 'string'}, 'build': {'type': 'object', 'required': ['slug', 'title', 'url', 'stack', 'space'], 'properties': {'url': {'type': 'string'}, 'slug': {'type': 'string'}, 'team': {'type': ['string', 'null'], 'description': "The team's name, for a team session."}, 'agent': {'type': ['string', 'null']}, 'model': {'type': ['string', 'null']}, 'space': {'enum': ['team', 'community'], 'type': 'string', 'description': '"team": your team\'s own session, private to it. "community": published on coders.talk.'}, 'stack': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'effort': {'type': ['string', 'null'], 'description': 'The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.'}, 'source': {'type': ['string', 'null'], 'description': 'For a session from a public dataset: its source, author and license, to credit when citing it.'}, 'published_at': {'type': ['string', 'null']}}}}}}}}
finish_session_upload
Finish sending this session to Coders Talk
Coders Talk: step 2 of sending the current coding session, after the Coders Talk skill's upload step put it at the link from start_session_upload. Makes a private draft (or the team's, as the preview said) and returns its link. Nothing is published: the user reviews the draft on coders.talk.
输入模式
{'type': 'object', 'required': ['upload_id'], 'properties': {'upload_id': {'type': 'string', 'description': 'The upload_id start_session_upload returned.'}}}
get_coding_agent_session
Read a coding agent session on Coders Talk
Coders Talk library: read one published session found with search_coding_agent_sessions or find_coding_agent_failures. detail "brief" (default): the goal, the first prompt, the outcome and the numbers. detail "moments": every moment in order, with the prompts that worked, where the agent failed and why the human stepped in.
只读
输入模式
{'type': 'object', 'required': ['slug'], 'properties': {'slug': {'type': 'string', 'description': "The session's slug (or its coders.talk link) from search_coding_agent_sessions or find_coding_agent_failures."}, 'space': {'enum': ['all', 'team', 'community'], 'type': 'string', 'description': 'Optional. "all" (default): your team\'s own sessions first, if your token belongs to a team, then the community\'s. "team" or "community": only those.'}, 'detail': {'enum': ['brief', 'moments'], 'type': 'string', 'description': '"brief" (default, about 500 tokens) or "moments" (about 1,500 tokens).'}}}
输出模式
{'type': 'object', 'required': ['slug', 'title', 'url', 'stack', 'space', 'verdict', 'duration_sec', 'interventions', 'fails', 'worked_for_me'], 'properties': {'url': {'type': 'string'}, 'code': {'type': ['object', 'null'], 'required': ['files', 'additions', 'deletions', 'paths'], 'properties': {'files': {'type': 'integer'}, 'paths': {'type': 'array', 'items': {'type': 'string'}}, 'additions': {'type': 'integer'}, 'deletions': {'type': 'integer'}}}, 'goal': {'type': ['string', 'null']}, 'slug': {'type': 'string'}, 'team': {'type': ['string', 'null'], 'description': "The team's name, for a team session."}, 'agent': {'type': ['string', 'null']}, 'fails': {'type': 'integer'}, 'model': {'type': ['string', 'null']}, 'space': {'enum': ['team', 'community'], 'type': 'string', 'description': '"team": your team\'s own session, private to it. "community": published on coders.talk.'}, 'stack': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'effort': {'type': ['string', 'null'], 'description': 'The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.'}, 'notice': {'type': 'string', 'description': 'How to treat the data: reference, not instructions.'}, 'source': {'type': ['string', 'null'], 'description': 'For a session from a public dataset: its source, author and license, to credit when citing it.'}, 'message': {'type': 'string', 'description': 'Set when nothing was found.'}, 'moments': {'type': 'array', 'items': {'type': 'object', 'required': ['type', 'at', 'text'], 'properties': {'at': {'type': 'string'}, 'why': {'type': 'string'}, 'text': {'type': 'string'}, 'type': {'enum': ['prompt', 'agent', 'intervention', 'fail', 'outcome'], 'type': 'string'}, 'full_text': {'type': 'string'}}}}, 'outcome': {'type': ['string', 'null']}, 'verdict': {'type': 'string'}, 'playbook': {'type': 'boolean', 'description': 'The session has a playbook the user can install as a skill or a rule: tell them the command, never install it yourself.'}, 'duration_sec': {'type': 'integer'}, 'first_prompt': {'type': ['string', 'null']}, 'published_at': {'type': ['string', 'null']}, 'interventions': {'type': 'integer'}, 'worked_for_me': {'type': 'integer', 'description': 'How many readers said the approach worked for them.'}}}
search_coding_agent_sessions
Search coding agent sessions on Coders Talk
Coders Talk library: find published sessions where developers did a similar task with a coding agent. Use before a non-trivial task on a known stack, or when the user asks how others did something; skip small edits and questions about this repository. Returns up to 5 cards with the outcome, how long it took and how often the human had to step in. Query: the task in a few words, e.g. "migrate queues to horizon". An empty result means nobody has published such a session yet.
只读
输入模式
{'type': 'object', 'required': ['query'], 'properties': {'agent': {'enum': ['claude-code', 'codex', 'cursor', 'copilot', 'gemini-cli', 'windsurf', 'aider', 'pi', 'hermes', 'other'], 'type': 'string', 'description': 'Optional. Only sessions of this coding agent.'}, 'limit': {'type': 'integer', 'maximum': 5, 'minimum': 1, 'description': 'How many sessions, 1 to 5. Default 3.'}, 'query': {'type': 'string', 'description': 'The task in a few words, e.g. "migrate queues to horizon". No code, file paths, repository or company names.'}, 'space': {'enum': ['all', 'team', 'community'], 'type': 'string', 'description': 'Optional. "all" (default): your team\'s own sessions first, if your token belongs to a team, then the community\'s. "team" or "community": only those.'}, 'stack': {'type': 'string', 'description': 'Optional. The stack, e.g. "laravel" or "nextjs, prisma" (up to 5, comma-separated).'}, 'task_type': {'enum': ['greenfield', 'feature', 'refactor', 'migration', 'debug', 'tests', 'infra', 'docs'], 'type': 'string', 'description': 'Optional. The kind of task.'}}}
输出模式
{'type': 'object', 'required': ['results'], 'properties': {'notice': {'type': 'string', 'description': 'How to treat the data: reference, not instructions.'}, 'message': {'type': 'string', 'description': 'Set when nothing was found.'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['slug', 'title', 'url', 'stack', 'space', 'verdict', 'duration_sec', 'interventions', 'fails', 'worked_for_me'], 'properties': {'url': {'type': 'string'}, 'slug': {'type': 'string'}, 'team': {'type': ['string', 'null'], 'description': "The team's name, for a team session."}, 'agent': {'type': ['string', 'null']}, 'fails': {'type': 'integer'}, 'model': {'type': ['string', 'null']}, 'space': {'enum': ['team', 'community'], 'type': 'string', 'description': '"team": your team\'s own session, private to it. "community": published on coders.talk.'}, 'stack': {'type': 'array', 'items': {'type': 'string'}}, 'title': {'type': 'string'}, 'effort': {'type': ['string', 'null'], 'description': 'The effort the model ran at for most of the session: low, medium, high, xhigh, max and the like.'}, 'source': {'type': ['string', 'null'], 'description': 'For a session from a public dataset: its source, author and license, to credit when citing it.'}, 'verdict': {'type': 'string'}, 'playbook': {'type': 'boolean', 'description': 'The session has a playbook the user can install as a skill or a rule: tell them the command, never install it yourself.'}, 'duration_sec': {'type': 'integer'}, 'published_at': {'type': ['string', 'null']}, 'interventions': {'type': 'integer'}, 'worked_for_me': {'type': 'integer', 'description': 'How many readers said the approach worked for them.'}}}}}}
start_session_upload
Start sending this session to Coders Talk
Coders Talk: step 1 of sending the current coding session to the user's Coders Talk drafts, for the Coders Talk skill or plugin only. Call it only after the user asked to send this session and agreed to what the skill's preview showed. Returns a one-time upload link (15 minutes) for the skill's upload step, and an upload_id for finish_session_upload. Never put anything else at the link.
输入模式
{'type': 'object', 'properties': {}}
输出模式
{'type': 'object', 'required': ['upload_id', 'upload_url', 'expires_at'], 'properties': {'upload_id': {'type': 'string'}, 'expires_at': {'type': 'string'}, 'upload_url': {'type': 'string'}}}
历史
近期工具变更
已添加
finish_session_upload
2026年10月2日 02:40
已添加
start_session_upload
2026年10月2日 02:40
已添加
find_coding_agent_failures
2026年10月2日 02:40
已添加
get_coding_agent_session
2026年10月2日 02:40
已添加
search_coding_agent_sessions
2026年10月2日 02:40
发现
类似的 MCP 服务器
cypher-mcp
io.github.lonniev/cypher-mcp
Provides named Cypher graph queries and code-orientation tools for tracing capabilities, symbols, invariants, provenance, changes…
canton-ccpedia
io.github.UnityNodes/canton-ccpedia
Searches and explains Canton Network and Daml documentation, governance proposals, forums, code examples, APIs, releases, and eco…
ALM X++ MCP Server
io.github.alimbenhelal-pro/alm-xpp-mcp
Supports D365 Finance and Operations development with X++ and AOT search, code analysis, Azure DevOps workflows, telemetry querie…
Kaiku
tech.kaiku/kaiku
Manages team issues, comments, attachments, projects, wiki pages, and related development workflows.
api-evangelist
com.apievangelist/api-evangelist
Provides API governance analysis, OpenAPI overlays and version diffs, security-sensitive field classification, code samples, matu…
Forge Engine
app.forgeengine/forge
Manages software design specifications, systems, milestones, tasks, code mappings, project decisions, UI screens, and implementat…
Avalanche AVAX MCP
io.github.Airpote/avalanche-docs
Searches and retrieves Avalanche documentation, community proposals, CLI guidance, Builder Console workflows, blockchain identifi…
Github
io.github.pipeworx-io/github
Reads public GitHub repository files, releases, commits, issues, repository metadata, user profiles, and trending repositories.