PluginBench
Skill
Official
Pass
Audit score 90

source-management

anthropics/knowledge-work-plugins

Manages connected MCP sources for enterprise search with priority ordering and rate limit awareness.

What is source-management?

Detects which MCP sources (chat, email, cloud storage, project tracker, CRM, knowledge base) are connected and available for search. Guides users to connect new sources, applies query-type-specific source prioritization, and handles rate limiting gracefully without blocking searches.

  • Detects and lists all connected MCP sources and their capabilities
  • Guides users through connecting new sources via MCP settings
  • Applies source priority ordering based on query type (decisions, status, documents, people, policies)
  • Handles rate limiting gracefully by continuing with other sources and informing users
  • Tracks source health and availability during a session
  • Supports custom MCP sources added to .mcp.json configuration

How to install source-management

npx skills add https://github.com/anthropics/knowledge-work-plugins --skill source-management
Prerequisites
  • MCP sources must be configured in .mcp.json
  • At least one MCP source connected and authenticated
  • MCP server running and accessible
Claude Code
Cursor
Windsurf
Cline

How to use source-management

  1. 1.Check which sources are currently connected by reviewing available tool prefixes
  2. 2.If needed, connect additional sources through MCP settings by adding server configurations
  3. 3.Run searches; the skill automatically applies priority ordering based on query type
  4. 4.Monitor source health status during searches; note any rate-limited sources
  5. 5.If a source is rate limited, continue with results from other sources and retry later

Use cases

Good for
  • Finding decisions by prioritizing chat and email sources where decisions are typically discussed
  • Checking project status by querying task tracker first, then supplementing with chat and documents
  • Locating documents by searching cloud storage first, then knowledge base and email
  • Identifying team members working on topics by searching chat authors and task assignees
  • Retrieving policy information from knowledge base and policy documents
Who it's for
  • Enterprise knowledge workers performing cross-source searches
  • Teams using multiple connected tools (Slack, email, Google Drive, Jira, Salesforce, etc.)
  • Users managing large volumes of distributed information
  • Organizations needing intelligent source prioritization for search

source-management FAQ

How do I know which sources are connected?

Check the available MCP tool prefixes. Each source (chat, email, cloud storage, project tracker, CRM, knowledge base) corresponds to a set of tools. If the tool prefix is available, the source is connected.

What should I do if a source is rate limited?

The skill will continue searching other sources and inform you that one source is temporarily rate limited. Results will come from available sources, and you can retry in a few minutes to include the rate-limited source.

How does source priority ordering work?

Different query types benefit from different source orders. Decision queries prioritize chat and email; status queries prioritize task tracker; document queries prioritize cloud storage; people queries prioritize chat; policy queries prioritize knowledge base. These are weights, not filters—all sources are still searched.

Can I add custom sources?

Yes. Add the MCP server configuration to .mcp.json, authenticate if required, and the source will be automatically detected and included in subsequent searches.

What happens if I have few sources connected?

The skill will suggest which additional sources you can connect (chat, email, cloud storage, project tracker, CRM, knowledge base) to expand your search results.

Full instructions (SKILL.md)

Source of truth, from anthropics/knowledge-work-plugins.


name: source-management description: Manages connected MCP sources for enterprise search. Detects available sources, guides users to connect new ones, handles source priority ordering, and manages rate limiting awareness. user-invocable: false

Source Management

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Knows what sources are available, helps connect new ones, and manages how sources are queried.

Checking Available Sources

Determine which MCP sources are connected by checking available tools. Each source corresponds to a set of MCP tools:

SourceKey capabilities
~~chatSearch messages, read channels and threads
~~emailSearch messages, read individual emails
~~cloud storageSearch files, fetch document contents
~~project trackerSearch tasks, typeahead search
~~CRMQuery records (accounts, contacts, opportunities)
~~knowledge baseSemantic search, keyword search

If a tool prefix is available, the source is connected and searchable.

Guiding Users to Connect Sources

When a user searches but has few or no sources connected:

You currently have [N] source(s) connected: [list].

To expand your search, you can connect additional sources in your MCP settings:
- ~~chat — messages, threads, channels
- ~~email — emails, conversations, attachments
- ~~cloud storage — docs, sheets, slides
- ~~project tracker — tasks, projects, milestones
- ~~CRM — accounts, contacts, opportunities
- ~~knowledge base — wiki pages, knowledge base articles

The more sources you connect, the more complete your search results.

When a user asks about a specific tool that is not connected:

[Tool name] isn't currently connected. To add it:
1. Open your MCP settings
2. Add the [tool] MCP server configuration
3. Authenticate when prompted

Once connected, it will be automatically included in future searches.

Source Priority Ordering

Different query types benefit from searching certain sources first. Use these priorities to weight results, not to skip sources:

By Query Type

Decision queries ("What did we decide..."):

1. ~~chat (conversations where decisions happen)
2. ~~email (decision confirmations, announcements)
3. ~~cloud storage (meeting notes, decision logs)
4. Wiki (if decisions are documented)
5. Task tracker (if decisions are captured in tasks)

Status queries ("What's the status of..."):

1. Task tracker (~~project tracker — authoritative status)
2. ~~chat (real-time discussion)
3. ~~cloud storage (status docs, reports)
4. ~~email (status update emails)
5. Wiki (project pages)

Document queries ("Where's the doc for..."):

1. ~~cloud storage (primary doc storage)
2. Wiki / ~~knowledge base (knowledge base)
3. ~~email (docs shared via email)
4. ~~chat (docs shared in channels)
5. Task tracker (docs linked to tasks)

People queries ("Who works on..." / "Who knows about..."):

1. ~~chat (message authors, channel members)
2. Task tracker (task assignees)
3. ~~cloud storage (doc authors, collaborators)
4. ~~CRM (account owners, contacts)
5. ~~email (email participants)

Factual/Policy queries ("What's our policy on..."):

1. Wiki / ~~knowledge base (official documentation)
2. ~~cloud storage (policy docs, handbooks)
3. ~~email (policy announcements)
4. ~~chat (policy discussions)

Default Priority (General Queries)

When query type is unclear:

1. ~~chat (highest volume, most real-time)
2. ~~email (formal communications)
3. ~~cloud storage (documents and files)
4. Wiki / ~~knowledge base (structured knowledge)
5. Task tracker (work items)
6. CRM (customer data)

Rate Limiting Awareness

MCP sources may have rate limits. Handle them gracefully:

Detection

Rate limit responses typically appear as:

  • HTTP 429 responses
  • Error messages mentioning "rate limit", "too many requests", or "quota exceeded"
  • Throttled or delayed responses

Handling

When a source is rate limited:

  1. Do not retry immediately — respect the limit
  2. Continue with other sources — do not block the entire search
  3. Inform the user:
Note: [Source] is temporarily rate limited. Results below are from
[other sources]. You can retry in a few minutes to include [source].
  1. For digests — if rate limited mid-scan, note which time range was covered before the limit hit

Prevention

  • Avoid unnecessary API calls — check if the source is likely to have relevant results before querying
  • Use targeted queries over broad scans when possible
  • For digests, batch requests where the API supports it
  • Cache awareness: if a search was just run, avoid re-running the same query immediately

Source Health

Track source availability during a session:

Source Status:
  ~~chat:        ✓ Available
  ~~email:        ✓ Available
  ~~cloud storage:  ✓ Available
  ~~project tracker:        ✗ Not connected
  ~~CRM:   ✗ Not connected
  ~~knowledge base:      ⚠ Rate limited (retry in 2 min)

When reporting search results, include which sources were searched so the user knows the scope of the answer.

Adding Custom Sources

The enterprise search plugin works with any MCP-connected source. As new MCP servers become available, they can be added to the .mcp.json configuration. The search and digest commands will automatically detect and include new sources based on available tools.

To add a new source:

  1. Add the MCP server configuration to .mcp.json
  2. Authenticate if required
  3. The source will be included in subsequent searches automatically