scifinder-route-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCIFINDER_ROUTE_TOKEN | No | Legacy single token for authentication. If not set, use SCIFINDER_ROUTE_USERS. | |
| SCIFINDER_ROUTE_USERS | No | Multi-user token configuration in format user1:token1:role1,user2:token2:role2. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| register_document | Register and parse a local SciFinder export file already visible to the server. |
| upload_document | Copy a server-visible file into the upload area, then register and parse it. |
| scan_inbox | Scan the NAS inbox for supported SciFinder exports and queue/register new files. |
| get_parse_job_status | Return parse job status, stage, and error details. |
| list_parse_jobs | List recent parse jobs, optionally filtered by status. |
| health_check | Return server health, configured paths, and indexed object counts. |
| get_config | Return the effective application config. Secrets are masked unless include_secrets is true. |
| update_config | Merge hot-reloadable application config updates into config.yaml and reload them. |
| validate_config | Validate the current application config and report settings that require container restart. |
| reload_config | Reload hot application config from config.yaml without restarting the container. |
| search_reaction_steps | Search extracted reaction steps by text and structured condition filters. |
| get_reaction_step | Return one structured reaction step. |
| get_reaction_provenance | Return source text/page/parser provenance for a reaction step. |
| reparse_document | Clear extracted reactions for a document and parse it again. |
| record_doi_verification | Record DOI source verification performed by an agent or browser workflow. |
| export_evaluation_set | Export extracted reaction steps as JSONL for manual labeling and regression checks. |
| retry_parse_job | Retry a failed or completed parse job by moving it back to the durable queue. |
| retry_failed_jobs | Retry recent failed parse jobs. |
| rebuild_vector_index | Generate embeddings for reaction steps using the configured embedding endpoint. |
| get_vector_index_status | Return vector index coverage, model, and last error. |
| semantic_search_reaction_steps | Search reaction steps semantically using the configured embedding endpoint. |
| search_compounds | Search the compound registry by name, CAS, SMILES, or InChIKey. |
| get_compound | Return compound metadata, aliases, and linked reactions. |
| merge_compounds | Merge source compound aliases/reaction links into a target compound. |
| search_by_smiles | Normalize a SMILES string when RDKit is available, then search compounds. |
| recognize_structure_image | Send an image region to a configured MolScribe/DECIMER/OSRA-style endpoint and register candidate SMILES. |
| compute_evaluation_metrics | Compute regression metrics from a gold-set JSONL file. |
| get_evaluation_status | Return the latest evaluation metrics. |
| backup_database | Create a SQLite database backup, or report Postgres backup guidance. |
| get_storage_usage | Return NAS data/upload/evidence storage usage. |
| cleanup_evidence_cache | Clean generated evidence/cache files without deleting source documents. |
| test_integration_endpoint | Test one configured integration endpoint: llm, embedding, ocr, document_parser, structure_recognition, postgres. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
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/kettly1260/scifinder-route-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server