Soracom Knowledge MCP Server
Server Details
Search SORACOM documentation: service guides, FAQ, API references, IoT recipes, etc.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- soracom/mcp
- GitHub Stars
- 0
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.3/5 across 3 of 3 tools scored.
Each tool has a clearly distinct purpose: get_document fetches full pages, search_api_docs focuses on API/CLI/SAM, and search_soracom_docs covers service guides and console how-tos. No overlap in functionality.
All tools follow a consistent verb_noun pattern with underscores (get_document, search_api_docs, search_soracom_docs). The naming is predictable and clear.
Three tools is slightly on the lower side but appropriate for a focused knowledge retrieval server. Each tool serves a necessary role, and the number feels well-scoped.
The tool set covers most retrieval needs: searching two distinct document types and fetching full pages. Minor gaps like listing all documents or browsing categories are absent, but the core workflow is complete.
Available Tools
3 toolsget_documentARead-onlyInspect
Fetch full markdown for a SORACOM documentation page. Also resolves API schema links. Exact URLs are attempted first.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | A search-result URL, or the full URL of a `#/schema/<Name>` link from search_api_docs. Must start with http:// or https://; pass it exactly as returned. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and openWorldHint. The description adds behavioral traits: it resolves API schema links and attempts exact URLs first (implying fallback). There is no contradiction with annotations.
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?
Two sentences, both front-loaded with the main action. Every word is necessary. No redundancy or fluff.
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 fetch tool with one parameter and no output schema, the description covers purpose, parameter source, and a behavioral note. It could mention error handling or return format, but it is adequate given low complexity.
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 input schema has 100% coverage on the single 'url' parameter, including a description. The tool description adds minimal extra context ('Exact URLs are attempted first') but does not significantly enhance understanding beyond the schema.
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 'Fetch full markdown for a SORACOM documentation page', specifying the action and resource. It also mentions resolving API schema links, distinguishing it from sibling search tools (search_api_docs, search_soracom_docs) which are for searching, not retrieving.
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 context on when to use this tool: after obtaining a URL from search results or schema links. The input schema further clarifies acceptable URL sources. However, it does not explicitly state when not to use it or name alternatives beyond the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_api_docsARead-onlyInspect
Search SORACOM API documentation, CLI references, and SAM permissions. Use for exact API endpoints, soracom-cli commands, or SAM permission strings. Use search_soracom_docs for service guides, console how-tos, pricing, or IoT recipes. Use get_document on #/schema/<Name> links in results to read full API schema fields.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | Optional OpenAPI tag such as 'Sim', 'DataEntry', 'Stats', or 'Query'. Exact, case-insensitive; discover valid tags from result api_tag fields. | |
| path | No | Optional API path fragment, matched as a case-insensitive substring excluding the version prefix — e.g. '/sims' or 'subscribers', not '/v1/sims'. | |
| query | No | Natural-language query or API endpoint name. Optional when tag, method, or path is supplied; omit to browse filtered operations. | |
| method | No | Optional HTTP method to narrow results (e.g. 'GET', 'POST'). Exact, case-insensitive match. | |
| language | No | Documentation language. Omit to auto-detect; set only to pin one language. | |
| max_results | No | Maximum results to return (1-32). Increase when exploring. | |
| search_mode | No | Search strategy: 'hybrid' combines keyword and vector search; 'keyword' matches exact API paths, operationIds, and parameter names; 'semantic' uses vector similarity only. | hybrid |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the description doesn't need to repeat safety info. However, it adds little beyond that, such as mentioning iterative tag discovery. No contradictions.
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?
Description is a single paragraph with front-loaded purpose. Each sentence adds value, though slightly verbose. No wasted 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?
For a 7-parameter search tool with no output schema, the description explains usage, alternatives, and parameter interactions (e.g., query optional with tag). Could describe result format but schema descriptions compensate.
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% with detailed parameter descriptions. The main description adds some usage context (e.g., omitting query to browse) but does not significantly extend meaning beyond the schema. Baseline 3 is appropriate.
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 tool searches SORACOM API documentation, CLI references, and SAM permissions, and distinguishes it from sibling tools (search_soracom_docs and get_document) by specifying exact use cases.
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?
Explicitly tells when to use this tool (for exact API endpoints, CLI commands, SAM permission strings) and when to use alternatives (search_soracom_docs for service guides, get_document for schema details).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_soracom_docsARead-onlyInspect
Search SORACOM service documentation, guides, and console how-to articles (user site, service overviews and pricing, IoT recipes). Covers SORACOM services, subscription plans, User Console operations, changelogs, blogs, devices, IoT Store, partners, contract terms, and use cases. Use search_api_docs for API references, CLI commands, or SAM permissions.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query in natural language related to SORACOM services or console usage | |
| market | No | End-user's deployment market, not the query language. Omit if unknown. | |
| language | No | Documentation language. Omit to auto-detect; set only to pin one language. This does not imply the user's market — use market for that. | |
| max_results | No | Maximum results to return (1-32). Increase when exploring. | |
| search_mode | No | Search strategy: 'hybrid' combines keyword and vector search; 'keyword' matches exact tokens; 'semantic' uses vector similarity only. | hybrid |
| document_names | No | Optional document-name scope filter. Omit when unsure; narrowing too early can hide relevant results. Each document has a fixed language; only in-scope languages are searched. Available documents: - blog.soracom.com (Japanese): Official blog: announcements, tutorials, event reports, and customer stories. - changelog.soracom.io (English): New feature releases, end-of-service notices, and pricing/spec changes. - changelog.soracom.io/ja (Japanese): New feature releases, end-of-service notices, and pricing/spec changes. - developers.soracom.io (English): SORACOM Developer Site docs. - iot-template-gallery.soracom.io (English): Ready-to-use IoT solution template setup guides. - iot-template-gallery.soracom.jp (Japanese): Ready-to-use IoT solution template setup guides. - iot-usecase.com (Japanese): IoT use cases showing SORACOM across industries. - soracom.io (English): Official blog: announcements, tutorials, event reports, and customer stories. - soracom.io/terms (English): Contract terms and conditions for SORACOM services in English, by region. - soracom.jp/iot-recipes (Japanese): Step-by-step IoT solution recipes with SORACOM. - soracom.jp/iot_basics (Japanese): Introductory IoT fundamentals and related technologies. - soracom.jp/partners (Japanese): SORACOM Partner Space and certified partner information. - soracom.jp/services (Japanese): SORACOM service overviews and pricing. - soracom.jp/store (Japanese): SORACOM IoT Store devices and starter kits. - soracom.jp/support_partners/certified_device (Japanese): SORACOM certified and compatible IoT device catalog. - soracom.jp/terms (Japanese): Contract terms and conditions (利用規約) for SORACOM services in Japanese. - support.soracom.io/hc/en-us (English): SORACOM support FAQs. - support.soracom.io/hc/ja (Japanese): SORACOM support FAQs. - users.soracom.io (Japanese): SORACOM User Site docs for service usage and configuration. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description is consistent with readOnlyHint and openWorldHint annotations. It explains the scope of documents covered and behavior of search modes (hybrid, keyword, semantic). No contradictions.
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?
Description is relatively long but well-structured. Purpose is front-loaded. The enumeration of coverage areas could be slightly condensed, but overall it is informative without being overly verbose.
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?
Description covers most aspects but does not describe the return format or structure of results. Since there is no output schema, this information would be helpful for agents to interpret results properly. Otherwise, it is complete for invocation guidance.
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 covers all parameters with descriptions (100% coverage). Description adds extra value by providing detailed explanations for document_names, including each document's language and content type. Usage hints for market, language, and document_names enhance semantic understanding.
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?
Description clearly states the tool searches SORACOM documentation and lists specific coverage areas. It distinguishes from the sibling tool search_api_docs, saying use that for API references, CLI commands, or SAM permissions. This provides clear purpose differentiation.
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 explicit guidance on when to use this versus search_api_docs. Also gives practical advice for parameters: omit market if unknown, auto-detect language, omit document_names if unsure. These help agents decide when and how to invoke.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!