This server allows you to search for Safety Data Sheets (SDS) for chemicals or products using the search_sds_by_name tool.
Search by name: Provide a chemical_name to find matching SDS records.
Fuzzy matching: Set is_contains to true for partial or misspelled name matching; false for an exact match.
Synonym matching: Use include_synonyms to also match known synonyms, though performance may be slower.
Limit results: Control the number of returned records with the limit parameter (default is 25).
Detailed results: Each match returns the following metadata:
id, product_name, manufacturer
cas_number, msds_number, revision_date
has_sds flag indicating document availability
sds_url – a direct link to the SDS document (usually a PDF)
Currently not supported:
Searching by CAS number
Filtering results by manufacturer
Fetching and extracting the full content of SDS documents
Click on "Deploy 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., "@sds-mcp-server find the SDS for acetone"
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.
An MCP server that lets Claude (or any MCP client) search for Safety Data Sheets (SDS) by chemical or product name, using chemicalsafety.com's SDS search.
search_sds_by_nameSearch for SDS records by chemical or product name.
Argument | Type | Default | Description |
| string | — | Chemical or product name to search for, e.g. |
| bool |
| Match names containing the text instead of requiring an exact match (useful for misspelled or partial names) |
| int |
| Max results to return (common chemicals can return 100+ matches) |
Returns a list of records with id, product_name, manufacturer, cas_number,
msds_number, revision_date, has_sds, and sds_url (a direct link to the SDS
document, usually a PDF).
Synonym matching (IncludeSynonyms) is intentionally not exposed — it's the source
endpoint's slowest query mode and was the main cause of Claude Science's local-connector
calls stalling past its response-latency comfort zone, with no real benefit for named
chemicals. is_contains covers the useful "fuzzy match" case within normal response
times.
Related MCP server: cds-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e .Copy .mcp.json.example to .mcp.json and update the paths to point at this repo's
.venv/bin/python3 and server.py:
cp .mcp.json.example .mcp.jsonThen edit the paths inside, restart Claude Code in this directory, and approve the project MCP server when prompted.
Claude Science connects to local MCP servers via a custom connector, which runs under a
macOS sandbox (sandbox-exec) with restricted process execution, filesystem access, and
network access. Getting this working needs both a sandbox exception (below) and the
connector itself.
Claude Science reads optional settings from ~/.claude-science/config.toml (create the
file if it doesn't exist — it's not created by default). Add this repo's path to
[sandbox] user_read_paths so the sandbox permits reading server.py and its
dependencies, and add chemicalsafety.com to [sandbox.network] allowed_domains so the
sandboxed process can actually reach the search endpoint:
[sandbox]
user_read_paths = [
"/Users/you/sds-mcp-server",
]
[sandbox.network]
allowed_domains = [
"chemicalsafety.com",
]This file is only read at startup, so restart Claude Science after editing it. See
the configuration file reference
for the full set of config.toml keys.
Run the setup steps above so .venv/ exists with dependencies installed in this repo.
In Claude Science, go to Settings > Connectors > Add connector > Local command.
Fill in:
Name: sds-lookup
Command (single field, the whole command line): the absolute path to this
repo's venv Python interpreter, including its version number, followed by the
absolute path to server.py, e.g.
/Users/you/sds-mcp-server/.venv/bin/python3.14 /Users/you/sds-mcp-server/server.pyRun ls .venv/bin | grep python3\\. to find your exact interpreter name (e.g.
python3.14). Using the unversioned python or python3 symlink instead fails
with sandbox-exec: execvp() of '.../.venv/bin/python' failed: Operation not permitted — the sandbox's exec check doesn't resolve the extra symlink hop those
names add, but the version-numbered binary resolves directly and is covered by the
user_read_paths grant from step 1.
Click Add, then approve the search_sds_by_name tool when Claude first tries to
use it (or set it to Always allow on the connector's page under Tools).
No PYTHONPATH or system-Python juggling needed — once the repo is in
user_read_paths, the sandbox can execute the venv's own interpreter directly, and it
already knows where its own site-packages are.
The chemicalsafety.com search endpoint is undocumented and returns 403 unless the
request includes browser-like User-Agent, Origin, and Referer headers — this is
already handled in sds_search.py.
Not yet implemented:
Search by CAS number
Filter by manufacturer
Fetch and extract full SDS document content (most links are PDFs)
Search for Safety Data Sheets (SDS) by chemical or product name.
Args: chemical_name: Chemical or product name to search for, e.g. "Acetone". is_contains: If True, match names containing this text instead of requiring an exact match (useful for partial or misspelled names). include_synonyms: If True, also match known synonyms of the chemical name. limit: Maximum number of results to return (the source can return 100+ matches for common chemicals, so this keeps responses manageable).
Returns: A list of matching records, each with: id, product_name, manufacturer, cas_number, msds_number, revision_date, has_sds, and sds_url (a direct link to the SDS document, usually a PDF).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| is_contains | No | ||
| chemical_name | Yes | ||
| include_synonyms | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden. It discloses that the source can return 100+ matches, describes the return fields in detail, and indicates sds_url is a direct PDF link. It doesn't explicitly mention read-only behavior, but search semantics imply it.
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 well-structured with clear Args and Returns sections. Every sentence serves a purpose—parameter explanations, usage tips, and return format—without unnecessary fluff. It is concise yet complete.
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 no annotations and no siblings, the description provides all essential context: what the tool does, how to tune behavior, and what the response contains. The output schema exists but the description still enumerates return fields, making it self-sufficient for an AI agent.
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 has 0% description coverage, so the description must compensate. It does so excellently, explaining each parameter's purpose, default behavior, and rationale (e.g., include_synonyms 'match known synonyms', limit keeps responses manageable). This goes far beyond the bare 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 it 'Search for Safety Data Sheets (SDS) by chemical or product name' using a specific verb and resource. Even without sibling tools, the purpose is unambiguous and distinct from any generic search action.
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 practical guidance on when to use the flags: is_contains is 'useful for partial or misspelled names' and limit is recommended because 'the source can return 100+ matches.' It lacks explicit alternatives or exclusions, but given no siblings, the context is adequate.
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.
v0.1.0search_sds_by_nameScored across 1 tool
Only one tool exists, so there is no possibility of ambiguity or overlap. The tool's purpose is clearly defined as searching for SDS by chemical or product name.
The single tool name 'search_sds_by_name' is consistent with a clear verb_noun pattern and clearly indicates its function. There are no other tools to conflict with.
With only one tool, the server feels thin for a domain that could reasonably include fetching by ID or listing all SDS. However, for a focused search-only server, a single tool may be acceptable, so this is borderline.
The tool provides comprehensive search options (exact, partial, synonyms, limit) and returns useful metadata including a direct URL to the SDS. Gaps include lack of direct retrieval by ID or pagination beyond a simple limit, but the core search use case is well covered.
Hosted MCP server for finding authoritative primary data sources and official portals.
MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).
MCP server for real-time product search by barcode (EAN, UPC, GTIN) or keyword on ean-search.org
An MCP server that through www.gdacs.org provides access to web‐based disaster information systems.
