Integration

BridgeDb integration

BridgeDb maps biological and chemical identifiers between databases: give a gene, protein or metabolite identifier with its database system code (Ensembl, Entrez Gene, HGNC, UniProt, ChEBI, Wikidata and about 150 more) and an organism, and get its equivalents in every other database or in one chosen database, one at a time or in batches. It also searches identifiers and attribute values such as gene symbols, returns an identifier's attributes (symbol, description, chromosome, chemical formula) and lists the organisms, databases and attribute names each organism supports. The single-source batch variants, the capped identifier search, the mapper property dump, the runtime version report and the HTML help page are not exposed. No authentication: the public webservice is free and keyless.

Connect BridgeDb How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in BridgeDb.Built from the 17 BridgeDb tools below, on the connection you add once.

What you can do with BridgeDb

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Xref, 3 operations

map_compact_identifierMap compact identifierGETMaps a compact identifier (Bioregistry prefix:id, the form map_identifier returns, such as ensembl:ENSG00000139618) to all its equivalents; the source database is taken from the prefix.
map_identifierMap identifierGETMaps one identifier (an organism, the system code of its database and the identifier) to all its equivalents in every other database, for example an Ensembl gene to its HGNC symbol, Entrez Gene id and UniProt proteins.
map_identifier_to_targetMap identifier to targetGETMaps one identifier to its equivalents in a single target database only, for example an Ensembl gene to its UniProt protein accessions.

Attr name, 1 operation

get_attributeGet attributeGETReturns the value of one attribute (named in attrName, for example Symbol) of one identifier. Without attrName it returns every attribute, like get_attributes.

Attribute, 1 operation

get_attributesGet attributesGETReturns every stored attribute of one identifier (such as Symbol, Description, Type, Chromosome, Synonym, or chemical attributes like InChIKey and SMILES), rather than its cross-references.

Attribute set, 1 operation

list_attribute_namesList attribute namesGETLists the attribute names stored for the organism (Symbol, Synonym, Description, Chromosome, Type, InChIKey, SMILES...), the values search_attributes and get_attribute accept as attrName.

Content, 1 operation

list_organismsList organismsGETLists the organisms loaded in the BridgeDb webservice, as an object mapping each short name (Human, Mouse, Yeast...) to its Latin name. Use either name as the organism of every other tool.

Datasource, 1 operation

list_data_sourcesList data sourcesGETReturns the whole BridgeDb database registry (about 150 databases), keyed by database name, with each database's system code, identifier pattern, example identifier and Bioregistry prefix. Use it to find the system code the other tools need.

Is free search supported, 1 operation

check_free_search_supportCheck free search supportGETTells whether the organism supports the free-text searches (search_identifiers and search_attributes).

Is mapping supported, 1 operation

check_mapping_supportCheck mapping supportGETTells whether identifiers of one database can be mapped to another for the organism. Call it before a mapping to tell an unsupported pair from a supported one with no hit.

Param, 1 operation

search_attributesSearch attributesGETSearches attribute values (gene symbol by default, or another attribute named in attrName) by substring and returns the identifiers that carry a matching value. Use list_attribute_names for the attribute names.

Search, 1 operation

search_identifiersSearch identifiersGETSearches the organism's identifiers by substring and returns matches with their database name. It returns at most one match per database, so pass a full or distinctive identifier. For gene symbols or other attribute values, use search_attributes.

Source data source, 1 operation

list_source_data_sourcesList source data sourcesGETLists the databases whose identifiers can be mapped FROM for the organism, by full name (Ensembl, Entrez Gene, HGNC, ChEBI...). Find a database's system code with list_data_sources.

Target d, 1 operation

batch_map_identifiers_to_targetBatch map identifiers to targetPOSTMaps many identifiers in one call to their equivalents in a single target database (targetDs). Each input line carries its own identifier and source system code.

Target data source, 1 operation

list_target_data_sourcesList target data sourcesGETLists the databases identifiers can be mapped TO for the organism, by full name. Find a database's system code with list_data_sources.

Xref exist, 1 operation

check_identifier_existsCheck identifier existsGETTells whether an identifier is known for the organism, without mapping it. Use it to tell an unknown identifier apart from a known one that has no equivalent in the requested database.

Xrefs batch, 1 operation

batch_map_identifiersBatch map identifiersPOSTMaps many identifiers in one call to all their equivalents. Each input line carries its own identifier and source system code, so one batch can mix databases.

Use BridgeDb from Claude Code, Cursor or Codex

Connect BridgeDb in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its BridgeDb operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect BridgeDb

Create your workspace
Sign up free. Nothing to install.
Connect BridgeDb once
BridgeDb needs no credential, so its tools work immediately.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.