Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SEO Experts MCP what are Harry Sanders' top SEO tactics?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Query the distilled point of view of real SEO experts, straight from your AI assistant.
This MCP server gives Claude, Cursor, or any MCP client a set of tools to ask "what does [SEO expert] actually say about [topic]?" and get back concrete, actionable tactics, each linked to the expert's original source video.
Built by That's Heaps, a fractional growth consultancy specialising in SEO and GEO (getting brands cited by AI answer engines).
Each expert is a separate "brain": their public content, transcribed and distilled into topic-tagged tactics.
Expert | Source | Tactics |
Harry Sanders (@harrysandersseo, StudioHawk) | 200 Instagram reels | 639 |
More experts are added over time. Each stays a distinct voice, never blended.
Related MCP server: YouTube MCP Server
list_seo_experts — who's in the corpus, with each expert's POV summary
query_seo_experts — filter tactics by topic / keyword / expert; every result links to the source video
get_expert_pov — an expert's signature view and where their corpus is rich vs thin
Requires Node 22+.
git clone https://github.com/thatsheaps/experts.git
cd experts && npm installAdd to your Claude Code / Claude Desktop MCP config:
{
"mcpServers": {
"seo-experts": {
"command": "node",
"args": ["/absolute/path/to/experts/server.mjs"]
}
}
}Then ask your assistant things like "query the SEO experts on GEO" or "what's Harry Sanders' take on link building?".
Every tactic links back to the expert's original video. These are distillations of public content, published to point people toward each expert's work, not to replace it. If you're one of the featured experts and want changes or removal, open an issue or email hello@thatsheaps.com and we'll action it promptly.
Method: public content scraped, transcribed (Whisper), distilled into tactics (Claude), stored as a queryable SQLite brain per expert. The same pipeline That's Heaps uses to ground client SEO/GEO work in real practitioner POV.
MIT (code). Distilled tactics remain the intellectual output of the named experts; this tool indexes and links to their work.
Get a specific SEO expert's signature point of view and where their corpus is rich vs thin. Use before representing their view.
| Name | Required | Description | Default |
|---|---|---|---|
| expert | Yes | Expert slug, e.g. harry-sanders |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds meaningful details about what the tool returns ('signature point of view' and 'corpus rich vs thin') and implies a read-only, preparatory operation. While it does not discuss errors or side effects, the nature of the tool (a getter) makes this sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences with the primary action front-loaded. Every word earns its place, and there is no redundant repetition of the tool name or schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one parameter, no output schema, and no annotations, the description covers the essential purpose and usage. It indicates the type of information returned ('point of view', 'corpus rich vs thin') and the appropriate context ('before representing their view'), making it complete enough for a simple getter tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema fully describes the single parameter 'expert' with an example ('harry-sanders'), so baseline is 3. The tool description does not add additional parameter-specific syntax or formatting details beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the specific resource ('a specific SEO expert's signature point of view') along with the distinguishing element ('where their corpus is rich vs thin'). This differentiates it from sibling tools like list_seo_experts and query_seo_experts, making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage context with 'Use before representing their view,' clearly indicating when this tool should be invoked. It does not explicitly mention alternatives or when not to use it, but the specific use case is clear enough to guide an agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the SEO experts available in this corpus, with their POV summary and tactic counts. Call this first to see who you can query.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of disclosing behavior. It states what is returned (POV summary, tactic counts) and implies read-only listing, but it does not offer deeper context like potential caveats, output limits, or authentication requirements. It is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two concise sentences, front-loading the primary purpose and providing a clear call-to-action. Every word adds value, with no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and no output schema, the description covers the return contents (POV summary, tactic counts) and the intended usage (first step). It is complete enough for the agent to understand when and how to call this tool, though it could optionally mention the absence of search/filtering.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the schema already covers everything. The description adds no parameter details, but none are needed. Baseline for 0 params is 4, and the description does not detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action ('List the SEO experts') and its scope ('available in this corpus'), plus the output details (POV summary, tactic counts). It also distinguishes itself from siblings by emphasizing this is the discovery tool to call first before querying experts.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit guidance is given: 'Call this first to see who you can query.' This establishes a clear usage context and ordering relative to siblings. However, it does not explicitly mention when not to use it or name alternatives directly, so it falls short of a full 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Query real SEO experts' distilled tactics. Filter by topic (strategy, content, links, technical, tools, local, GEO/AI), a keyword, and/or a specific expert slug. Returns actionable tactics each linked to the expert's original source video.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max tactics to return (default 25) | |
| topic | No | One of: strategy, content, links, technical, tools, local, GEO/AI | |
| expert | No | Expert slug (e.g. harry-sanders); omit to query all experts | |
| keyword | No | Free-text match against the tactic text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses output format ('Returns actionable tactics each linked to the expert's original source video') and implies a read-only operation ('Query'). It does not mention pagination or rate limits, but these are not critical for a simple query tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the core purpose, and contains no redundant or filler language. Every sentence contributes meaningful information about what the tool does, how to filter, and what it returns.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple query tool with no output schema, the description sufficiently covers the return format and available filters. It omits the default limit behavior, but the schema documents the limit parameter, and the absence of nested objects or required params keeps complexity low.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, giving a baseline of 3. The description adds value by explicitly stating filters can be combined ('and/or') and enumerates the topic options, exceeding the schema's per-property descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb+resource: 'Query real SEO experts' distilled tactics.' It clearly distinguishes from siblings (list_seo_experts and get_expert_pov) by emphasizing filtered tactic retrieval with topic, keyword, and expert slug options.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides clear context: this tool is for querying/filtering tactics, not for listing experts or getting a single POV. However, it does not explicitly name alternatives or state when not to use it, only implying the use case through filter descriptions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get_expert_povlist_seo_expertsquery_seo_expertsEach tool has a clear, distinct role: listing experts, querying tactics, and retrieving a specific expert's POV. There is minimal overlap, and the descriptions reinforce the boundaries.
Tool names follow a verb-first pattern with snake_case, but mix verbs (list, query, get) and object naming (seo_experts vs expert_pov). This is still predictable and readable, with only minor deviations.
Three tools is well-scoped for a niche knowledge-query server. Each tool fills an essential role without redundancy or bloat.
The tool set covers the full discovery and query lifecycle: list to see options, query to search tactics, and get for deep-dive POV. No obvious missing operations for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Real SEO data for AI assistants: page audits, Keyword Planner volumes, Search Console history.
Query your SEO data in plain language: rankings, audits, backlinks, competitors and AI visibility.
SEO answers for AI agents: Search Console reads free, plus competitor, keyword, backlink, SERP data.
SEO research, audits, backlinks, GSC, and content workflow tools for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/thatsheaps/experts'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
