9-axis-human-sonar-mcp
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., "@9-axis-human-sonar-mcpFold the state [1,0,2,0,0,1,0]"
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.
9-axis-human-sonar-mcp
Model Context Protocol server for 9-axis conversation intelligence. Gives any MCP-aware LLM client (Claude Code, Claude Desktop, Cursor, etc.) tools to map transcripts across nine dimensions -- seven primes plus substrate (◊) and theta (θ).
Algorithms extracted verbatim from 9-Axis Human Sonar.
Install
npm install -g @ai-native-solutions/9-axis-human-sonar-mcpOr run without installing:
npx @ai-native-solutions/9-axis-human-sonar-mcpRelated MCP server: fallcrm-elite-mcp
Wire into Claude Desktop
~/.config/claude/claude_desktop_config.json (macOS/Linux) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"9-axis-human-sonar": {
"command": "npx",
"args": ["-y", "@ai-native-solutions/9-axis-human-sonar-mcp"]
}
}
}Restart Claude Desktop. The tools appear in the model's toolbox.
Wire into Claude Code
Add to ~/.claude.json:
{
"mcpServers": {
"9-axis-human-sonar": {
"command": "npx",
"args": ["-y", "@ai-native-solutions/9-axis-human-sonar-mcp"]
}
}
}Tools
sonar_map_transcript
Map a transcript across the 9 axes.
{ "text": "COACH: ...\nCLIENT: ...", "focus": "CLIENT" }Returns { axis_scores, thin, defended, strongest, weakest, turns_analysed, focus }.
sonar_next_probe
Suggest a probe targeting the weakest axis.
{ "current_map": { "substrate": {...}, "bloom": {...}, ... } }Returns { axis, sym, name, probe }.
sonar_export
Schema-tag a map for storage.
Resources
9-axis://axes-- full axis definitions (prime, symbol, name, question, keyword sets)9-axis://probes-- four probes per axis
Companion repos
SDK: 9-axis-human-sonar-sdk -- programmatic API
API: 9-axis-human-sonar-api -- HTTP server + Docker
Tool: 9-axis-human-sonar -- shipping HTML app
License
MIT -- AI-Native Solutions.
Available Tools
3 toolssonar_exportB
Serialise a sonar map to schema-tagged JSON for storage or downstream tools.
| Name | Required | Description | Default |
|---|---|---|---|
| map | Yes | A sonar map object. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates the operation is a serialization (non-destructive) and specifies the output format. However, without annotations, it lacks explicit mention of read-only behavior or any side effects.
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 a single, dense sentence with no wasted words. It is front-loaded and immediately informative.
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?
The description covers the core function and output format, but with no output schema, it could better describe the return value or constraints. Adequate for a simple 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?
Schema description coverage is 100% (the only parameter has a description). The tool description does not add additional meaning beyond reiterating the schema, so it meets but does not exceed the baseline.
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 (serialise), the object (sonar map), and the output format (schema-tagged JSON). It is distinct from sibling tools in function, though it doesn't explicitly differentiate.
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?
No guidance is provided on when to use this tool versus alternatives (sonar_map_transcript, sonar_next_probe). The agent must infer the appropriate context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
sonar_map_transcriptA
Map a transcript across the 9 axes (7 primes + substrate + theta). Returns per-axis presence, fidelity, coherence, composite, verdict; plus thin/defended axis lists and strongest/weakest.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Raw transcript. Speaker-prefixed lines (COACH: ..., CLIENT: ...) or plain text. | |
| focus | No | Optional speaker label to analyse. Auto-detects the wordiest speaker if omitted. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the tool is read-only (mapping/analysis) and specifies what it returns (per-axis metrics, lists). It does not mention side effects, auth, or rate limits, but the operation is clearly non-destructive.
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 a single, well-structured sentence that front-loads the action and efficiently lists return values. No filler or unnecessary words.
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?
Given the complexity (9 axes) and no output schema, the description provides sufficient detail about the return structure (presence, fidelity, etc.) and lists. It omits examples or formats but covers key outputs.
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 coverage is 100%, so the schema already describes both parameters adequately. The description adds context about the tool's output but does not add new meaning to the parameters beyond what the schema 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 ('Map a transcript across the 9 axes') and specifies the return values, making the tool's purpose clear. However, it does not distinguish from sibling tools (sonar_export, sonar_next_probe), which would merit a 5.
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?
No guidance is provided on when to use this tool versus alternatives or when not to use it. The description only explains what the tool does, lacking explicit usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
sonar_next_probeA
Given a current sonar map (from sonar_map_transcript), suggest the next probe targeting the weakest axis.
| Name | Required | Description | Default |
|---|---|---|---|
| current_map | Yes | The axis_scores object from a previous sonar_map_transcript call. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It describes the input and purpose but does not disclose whether the tool is read-only, whether it has side effects, or any authorization requirements. For a suggestion tool, these are less critical but still a gap.
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 a single, well-structured sentence that delivers the essential information upfront. Every word serves a purpose, 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?
The tool has one parameter and no output schema. The description adequately explains the input context by referencing 'sonar_map_transcript', but it does not describe the output format of the suggestion, which would be helpful for an agent anticipating the result.
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?
Despite 100% schema coverage, the description adds value by explaining that 'current_map' should be the axis_scores object from a previous call, which goes beyond the schema's type information. This provides concrete guidance for the parameter.
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 uses a specific verb ('suggest') and resource ('next probe'), clearly indicating the tool's function. It distinguishes itself from siblings by referencing the output of 'sonar_map_transcript' and specifying 'weakest axis' as the targeting criterion.
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 clear context by stating the tool should be given a 'current sonar map from sonar_map_transcript', implying a proper usage sequence. However, it does not explicitly state when not to use or mention alternatives beyond the implicit workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
3 tool updates
v1.0.0- First observed
sonar_export - First observed
sonar_map_transcript - First observed
sonar_next_probe
TDQS
Each tool has a distinct purpose: export for serialization, map_transcript for analysis, and next_probe for suggesting next steps. No functional overlap.
All tools use a consistent 'sonar_' prefix with verb_noun structure and snake_case throughout.
3 tools is slightly minimal but covers the core workflow of mapping, exporting, and probing. The scope is narrow, so the count feels appropriate.
The set covers the primary lifecycle: create a map, export it, and get a next probe. Missing potential tools like listing axes or comparing maps, but not critical for the stated purpose.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP gateway federating 22 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Auditable MCP server for PubMed, Europe PMC, ClinicalTrials.gov, and bioRxiv/medRxiv queries
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server for foldkit that exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client.MIT
- AlicenseNot gradedqualityFmaintenanceMCP server for foldkit that exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources for use in any MCP client.MIT
- AlicenseNot gradedqualityFmaintenanceMCP server for foldkit that exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for foldkit that exposes the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sjgant80-hub/9-axis-human-sonar-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server