# How to integrate Semanticscholar MCP with Hermes ```json { "title": "How to integrate Semanticscholar MCP with Hermes", "toolkit": "Semanticscholar", "toolkit_slug": "semanticscholar", "framework": "Hermes", "framework_slug": "hermes-agent", "url": "https://composio.dev/toolkits/semanticscholar/framework/hermes-agent", "markdown_url": "https://composio.dev/toolkits/semanticscholar/framework/hermes-agent.md", "updated_at": "2026-05-06T08:27:17.781Z" } ``` ## Introduction Hermes is a 24/7 autonomous agent that lives on your computer or server — it remembers what it learns and evolves as your usage grows. This guide explains the easiest and most robust way to connect your Semanticscholar account to Hermes. You can do this through either Composio Connect CLI or Composio Connect MCP. For personal use we recommend the CLI, but you won't go wrong with MCP either. ## Also integrate Semanticscholar with - [OpenAI Agents SDK](https://composio.dev/toolkits/semanticscholar/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/semanticscholar/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/semanticscholar/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/semanticscholar/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/semanticscholar/framework/codex) - [OpenClaw](https://composio.dev/toolkits/semanticscholar/framework/openclaw) - [CLI](https://composio.dev/toolkits/semanticscholar/framework/cli) - [Google ADK](https://composio.dev/toolkits/semanticscholar/framework/google-adk) - [LangChain](https://composio.dev/toolkits/semanticscholar/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/semanticscholar/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/semanticscholar/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/semanticscholar/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/semanticscholar/framework/crew-ai) ## TL;DR ### What is Composio Connect? Composio Connect is a consumer offering that lets anyone plug 1,000+ applications directly into their agent harness — including Hermes. It can: - Search and load tools from relevant toolkits on-demand, reducing context usage. - Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM. - Manage app authentication end-to-end with zero manual overhead. ## Connect Semanticscholar to Hermes ### Integrating Semanticscholar with Hermes ### Using Composio Connect CLI 1. Install the Composio CLI Run the install script directly, or paste https://composio.dev/hermes into your Hermes chat box to have it installed for you. ```bash curl -fsSL https://composio.dev/install | bash ``` ## What is the Semanticscholar MCP server, and what's possible with it? The Semanticscholar MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Semantic Scholar account. It provides structured and secure access to scholarly data, so your agent can search for academic papers, retrieve detailed author profiles, analyze citations, and explore references or publication histories on your behalf. - Comprehensive literature search and discovery: Let your agent search for academic papers by topic, author, or relevance and retrieve lists of matching publications with rich metadata. - In-depth paper and author insights: Ask your agent to fetch detailed information about specific papers—including titles, abstracts, authors, and publication years—or get complete profiles for researchers and their entire body of work. - Citation and reference analysis: Enable your agent to trace the impact of a paper by pulling its citations or explore the foundational research it builds upon by listing its references. - Batch retrieval for large-scale research: Efficiently gather details on multiple papers or authors at once, streamlining reviews and bibliometric analyses across large datasets. - Bulk and relevance-based queries: Use advanced bulk search and filtering to identify up to thousands of papers at a time, making it easy for your agent to support systematic literature reviews and academic data exploration. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `SEMANTICSCHOLAR_DETAILS_ABOUT_AN_AUTHOR` | Details about an author | Examples: https://api.semanticscholar.org/graph/v1/author/1741101 returns the author's authorid and name. https://api.semanticscholar.org/graph/v1/author/1741101?fields=url,papers returns the author's authorid, url, and list of papers. each paper has its paperid plus its title. https://api.semanticscholar.org/graph/v1/author/1741101?fields=url,papers.abstract,papers.authors returns the author's authorid, url, and list of papers. each paper has its paperid, abstract, and list of authors. in that list of authors, each author has their authorid and name. limitations: can only return up to 10 mb of data at a time. | | `SEMANTICSCHOLAR_DETAILS_ABOUT_AN_AUTHOR_S_PAPERS` | Details about an author s papers | Retrieves a list of papers authored by a specific researcher identified by their unique semantic scholar author id. this endpoint is particularly useful for conducting literature reviews, analyzing an author's body of work, or tracking a researcher's publications over time. it provides a comprehensive view of an author's contributions to their field of study. the endpoint returns only the papers associated with the specified author and does not include co-authored works where the specified author is not listed as a primary author. note that the response may be paginated for authors with a large number of publications, and additional api calls might be necessary to retrieve the complete list of papers. | | `SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER` | Details about a paper | Examples: https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b returns a paper with its paperid and title. https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b?fields=url,year,authors returns the paper's paperid, url, year, and list of authors. each author has authorid and name. https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b?fields=citations.authors returns the paper's paperid and list of citations. each citation has its paperid plus its list of authors. each author has their 2 always included fields of authorid and name. limitations: can only return up to 10 mb of data at a time. | | `SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER_S_AUTHORS` | Details about a paper s authors | Retrieves the list of authors for a specific paper identified by its unique paper id in the semantic scholar database. this endpoint is useful when you need detailed information about the contributors to a particular academic publication. it provides access to the author data associated with the paper, which may include names, affiliations, and potentially other metadata. this tool should be used when users require author information for a known paper, such as when exploring collaborations or tracking an author's body of work. it does not provide the full paper content or other paper metadata beyond author information. | | `SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER_S_CITATIONS` | Details about a paper s citations | Retrieves a list of citations for a specific academic paper using its unique semantic scholar paper id. this endpoint is useful for researchers and developers who want to explore the impact and connections of a particular academic work within the broader scientific literature. it provides information about other papers that have cited the specified paper, allowing users to trace the influence of research and discover related works. the endpoint should be used when analyzing the reception and impact of a specific paper, building citation networks, or conducting bibliometric studies. it does not provide the full text of citing papers or detailed information about the citations beyond basic metadata. | | `SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER_S_REFERENCES` | Details about a paper s references | Retrieves the list of references cited by a specific paper in the semantic scholar database. this endpoint allows users to explore the scholarly context of a publication by accessing its bibliography. it's particularly useful for understanding the foundation of a paper's research, tracing the development of ideas, or conducting literature reviews. the tool returns details about the cited papers, which may include their titles, authors, publication dates, and semantic scholar ids. it should be used when analyzing a paper's sources or investigating the connections between different academic works. note that this endpoint only provides outgoing references (papers cited by the specified paper) and not incoming citations (papers that cite the specified paper). | | `SEMANTICSCHOLAR_GET_DETAILS_FOR_MULTIPLE_AUTHORS_AT_ONCE` | Get details for multiple authors at once | Retrieves detailed information for multiple authors from semantic scholar in a single api call. this endpoint allows users to efficiently fetch data for a batch of authors by providing their unique semantic scholar ids. it's particularly useful for applications that need to gather information on multiple authors simultaneously, reducing the number of individual api calls required. the endpoint accepts a list of author ids and returns comprehensive details for each author, which may include their publications, citations, and other relevant academic information. while the exact response structure is not specified in the given schema, users can expect rich metadata about the requested authors. | | `SEMANTICSCHOLAR_GET_DETAILS_FOR_MULTIPLE_PAPERS_AT_ONCE` | Get details for multiple papers at once | The semanticscholar paper batch endpoint allows users to retrieve data for multiple academic papers in a single api call. this endpoint is particularly useful when you need to fetch information for a batch of papers efficiently, reducing the number of individual api requests. it accepts an array of paper ids and returns the corresponding data for each paper. use this endpoint when you have a list of known paper ids and want to retrieve their details simultaneously. keep in mind that while there's no specified limit on the number of ids you can send, very large batches may be subject to api rate limiting or response size restrictions. | | `SEMANTICSCHOLAR_PAPER_BULK_SEARCH` | Paper bulk search | Behaves similarly to /paper/search, but is intended for bulk retrieval of basic paper data without search relevance: text query is optional and supports boolean logic for document matching. papers can be filtered using various criteria. up to 1,000 papers will be returned in each call. if there are more matching papers, a continuation "token" will be present. the query can be repeated with the token param added to efficiently continue fetching matching papers. returns a structure with an estimated total matches, batch of matching papers, and a continuation token if more results are available. limitations: nested paper data, such as citations, references, etc, is not available via this method. up to 10,000,000 papers can be fetched via this method. for larger needs, please use the datasets api to retrieve full copies of the corpus. | | `SEMANTICSCHOLAR_PAPER_RELEVANCE_SEARCH` | Paper relevance search | The searchpapers endpoint allows users to search for academic papers within the semantic scholar database. it provides a powerful way to discover relevant scientific literature based on user-defined search criteria. this endpoint should be used when researchers, students, or developers need to find papers related to specific topics, authors, or time periods. the search functionality supports various query parameters to refine and customize the search results, making it suitable for both broad exploratory searches and targeted inquiries. however, users should be aware that the search is limited to papers indexed by semantic scholar, and very recent publications might not be immediately available. the endpoint returns a list of papers matching the search criteria, along with selected metadata fields, facilitating efficient literature review and analysis. | | `SEMANTICSCHOLAR_PAPER_TITLE_SEARCH` | Paper title search | Behaves similarly to /paper/search, but is intended for retrieval of a single paper based on closest title match to given query. examples: https://api.semanticscholar.org/graph/v1/paper/search/match?query=construction of the literature graph in semantic scholar returns a single paper that is the closest title match. each paper has its paperid, title, and matchscore as well as any other requested fields. https://api.semanticscholar.org/graph/v1/paper/search/match?query=totalgarbagenonsense returns with a 404 error and a "title match not found" message. limitations: will only return the single highest match result. | | `SEMANTICSCHOLAR_SEARCH_FOR_AUTHORS_BY_NAME` | Search for authors by name | The authorsearch endpoint allows users to search for authors within the semantic scholar database. it provides a way to find academic authors based on their names or other identifying information. this endpoint is particularly useful when you need to retrieve author metadata, such as their publications, affiliations, or research areas. the search functionality supports partial name matches and is case-insensitive, making it flexible for various search scenarios. use this endpoint when you want to discover authors or verify author information in the context of academic research. note that the search results may be limited and paginated, so multiple requests might be necessary for comprehensive results. | | `SEMANTICSCHOLAR_SUGGEST_PAPER_QUERY_COMPLETIONS` | Suggest paper query completions | To support interactive query-completion, return minimal information about papers matching a partial query example: https://api.semanticscholar.org/graph/v1/paper/autocomplete?query=semanti | | `SEMANTICSCHOLAR_TEXT_SNIPPET_SEARCH` | Text snippet search | Return the text snippets that most closely match the query. text snippets are excerpts of approximately 500 words, drawn from a paper's title, abstract, and body text, but excluding figure captions and the bibliography. it will return the highest ranked snippet first, as well as some basic data about the paper it was found in. examples: https://api.semanticscholar.org/graph/v1/snippet/search?query=the literature graph is a property graph with directed edges&limit=1 returns a single snippet that is the highest ranked match. each snippet has text, snippetkind, section, annotation data, and score. as well as the following data about the paper it comes from: corpusid, title, authors, and openaccessinfo. limitations: you must include a query. if you don't set a limit, it will automatically return 10 results. the max limit allowed is 1000. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Semanticscholar MCP server provides comprehensive access to Semanticscholar operations through Composio. Once connected, Hermes can perform all major Semanticscholar actions on your behalf using natural language commands. ## Complete Code None listed. ## Conclusion ### Way Forward With Semanticscholar connected, Hermes can now act on your behalf whenever it detects a relevant task or you ask it to. From here, you can extend Hermes further: - Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Hermes can do for you. - Build workflows across tools: Once multiple apps are connected, Hermes can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft. - Let it learn your patterns: The more you use Hermes, the better it gets at anticipating how you'd handle recurring tasks. Give it feedback on drafts and decisions, and it will adapt. If you run into trouble or want to share what you've built, join the [community](https://discord.com/invite/composio) or check out the [Docs](https://docs.composio.dev?utm_source=toolkits&utm_medium=framework_template&utm_campaign=hermes&utm_content=docs) for deeper configuration options. ## How to build Semanticscholar MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/semanticscholar/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/semanticscholar/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/semanticscholar/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/semanticscholar/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/semanticscholar/framework/codex) - [OpenClaw](https://composio.dev/toolkits/semanticscholar/framework/openclaw) - [CLI](https://composio.dev/toolkits/semanticscholar/framework/cli) - [Google ADK](https://composio.dev/toolkits/semanticscholar/framework/google-adk) - [LangChain](https://composio.dev/toolkits/semanticscholar/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/semanticscholar/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/semanticscholar/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/semanticscholar/framework/llama-index) - [CrewAI](https://composio.dev/toolkits/semanticscholar/framework/crew-ai) ## Related Toolkits - [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed. - [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service. - [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows. - [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow. - [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows. - [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application. - [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities. - [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization. - [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications. - [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations. - [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key. - [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient. - [Botbaba](https://composio.dev/toolkits/botbaba) - Botbaba is a platform for building, managing, and deploying conversational AI chatbots across messaging channels. It streamlines chatbot automation, making it easier to integrate AI into customer interactions. - [Botpress](https://composio.dev/toolkits/botpress) - Botpress is an open-source platform for building, deploying, and managing chatbots. It helps teams automate conversations and deliver rich, interactive messaging experiences. - [Chatbotkit](https://composio.dev/toolkits/chatbotkit) - Chatbotkit is a platform for building and managing AI-powered chatbots using robust APIs and SDKs. It lets you easily add conversational AI to your apps for better user engagement. - [Cody](https://composio.dev/toolkits/cody) - Cody is an AI assistant built for businesses, trained on your company's knowledge and data. It delivers instant answers and insights, tailored for your team. - [Context7 MCP](https://composio.dev/toolkits/context7_mcp) - Context7 MCP delivers live, version-specific code docs and examples right from the source. It helps developers and AI agents instantly retrieve authoritative programming info—no more out-of-date docs. - [Customgpt](https://composio.dev/toolkits/customgpt) - CustomGPT.ai lets you build and deploy chatbots tailored to your own data and business needs. Get precise and context-aware AI conversations without writing code. - [Datarobot](https://composio.dev/toolkits/datarobot) - Datarobot is a machine learning platform that automates model development, deployment, and monitoring. It empowers organizations to quickly gain predictive insights from large datasets. - [Deepgram](https://composio.dev/toolkits/deepgram) - Deepgram is an AI-powered speech recognition platform for accurate audio transcription and understanding. It enables fast, scalable speech-to-text with advanced audio intelligence features. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Semanticscholar MCP? With a standalone Semanticscholar MCP server, the agents and LLMs can only access a fixed set of Semanticscholar tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Semanticscholar and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Hermes? Yes, you can. Hermes fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Semanticscholar tools. ### Can I manage the permissions and scopes for Semanticscholar while using Tool Router? Yes, absolutely. You can configure which Semanticscholar scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Semanticscholar data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)