How do I use edi-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@edi-mcp find recent LTER data packages about stream discharge in Wisconsin" 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.

edi-mcp

by idss-mesa

Overview Schema Source Related Servers Discussions Admin

Python

Remote

edi-mcp

MCP 2026-07-28 License: MIT Docs

A Model Context Protocol server (spec 2026-07-28) for the Environmental Data Initiative (EDI) PASTA+ data repository. It lets agents search, inspect, preview, download and cite LTER and EDI ecological data packages.

Documentation: https://idss-mesa.github.io/edi-mcp/

Status: under construction. The discovery tools (edi_ping, search, list scopes/identifiers/revisions) and the package tools (edi_get_package, edi_get_metadata, edi_list_entities) work; the rest of the tools below are planned. See DESIGN.md for decisions and RESEARCH.md for verified API facts.

Installation

Full instructions for macOS, Linux and Windows: https://idss-mesa.github.io/edi-mcp/getting-started/install/.

Install script

scripts/install.sh registers the server with every supported agent it finds. It creates the server environment with uv sync if .venv/bin/edi-mcp is missing, prefers each agent's own CLI when one is installed (claude mcp add, codex mcp add, gemini mcp add) and otherwise merges an entry into the agent's config file, keeping everything else in the file and leaving a .bak copy. It needs bash and uv.

git clone https://github.com/idss-mesa/edi-mcp.git && cd edi-mcp
scripts/install.sh                               # every agent detected on this machine
scripts/install.sh --with-key                    # also store EDI_API_KEY (read from env or a hidden prompt)
scripts/install.sh --agents all --dry-run        # preview the change for every agent
scripts/install.sh --agents claude,goose         # just Claude Code and Goose
scripts/install.sh --scope project               # project-level config (claude, codex, gemini, opencode)
scripts/install.sh --env EDI_MCP_SERVER__LOG_LEVEL=debug   # any extra environment variable
scripts/install.sh --uninstall                   # remove the registration everywhere

Agent	What the script does
`claude` (Claude Code)	`claude mcp add --scope user edi -- /path/to/edi-mcp/.venv/bin/edi-mcp`
`claude-desktop`	adds `mcpServers.edi` to `claude_desktop_config.json`
`codex` (OpenAI Codex CLI)	`codex mcp add edi -- …`, or an `[mcp_servers.edi]` table in `~/.codex/config.toml`
`gemini` (Gemini CLI)	`gemini mcp add --scope user edi …`, or `mcpServers.edi` in `~/.gemini/settings.json`
`goose`	adds an `edi` stdio extension to `~/.config/goose/config.yaml`
`opencode`	adds `mcp.servers.edi` (v2) or `mcp.edi` (v1) to `~/.config/opencode/opencode.json`

The script writes absolute paths, because desktop apps do not inherit your shell PATH. There is no option that takes the key itself; with --with-key the key is stored in plain text in each agent's config (written owner-only) and never printed. On Windows, run it from Git Bash or follow the manual steps; restart desktop apps after installing.

Manual

uv tool install git+https://github.com/idss-mesa/edi-mcp
claude mcp add edi -s user -e EDI_API_KEY="$EDI_API_KEY" -- edi-mcp

Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows, ~/.config/Claude/claude_desktop_config.json on Linux):

{
  "mcpServers": {
    "edi": {
      "command": "/ABSOLUTE/PATH/TO/edi-mcp",
      "args": [],
      "env": { "EDI_API_KEY": "paste-your-key-here" }
    }
  }
}

Other clients (Codex CLI, Gemini CLI, Goose, OpenCode, VS Code, hosted HTTP): https://idss-mesa.github.io/edi-mcp/getting-started/clients/.

Related MCP server: mcp-datacite

Authentication

Since 2026-07-30 EDI requires an API key for every PASTA REST call, including public reads. Create a free key at https://auth.edirepository.org (Profile → API keys) and set it as EDI_API_KEY. Without a key, edi-mcp falls back to the anonymous DataONE replicas of EDI content: search, metadata, entity download and citations work, while quality reports, lineage, change feeds and read counts need a key.

Planned tools

Tool	Purpose
`edi_search_packages`	Search packages by keyword, scope/site, author, time and bounding box
`edi_list_scopes` / `edi_list_identifiers` / `edi_list_revisions`	Browse the repository hierarchy
`edi_get_package`	DOI, landing page, entities and sizes for one package revision
`edi_get_metadata`	Compact projection of the EML metadata
`edi_list_entities`	Data entities with names, sizes, checksums, formats and attributes
`edi_preview_entity`	First rows of a tabular entity
`edi_get_citation`	Formatted citation (ESIP, DRYAD, BibTeX)
`edi_get_quality_report`	PASTA congruence-check summary (key required)
`edi_get_lineage`	Provenance sources and descendants (key required)
`edi_recent_changes`	Recent inserts, updates and deletes (key required)
`edi_get_read_counts`	Download/read counts (key required)
`edi_download_entities` / `edi_download_package`	Save data locally (stdio only)
`edi_ping`	Server, backend and key status

License

Available Tools

8 tools

edi_get_metadataRead a package's EML metadata

Read-onlyIdempotent

The package's EML, projected to compact sections: overview (abstract, keywords, dates), people (creators, contacts with ORCIDs), coverage (bounding boxes, date ranges, taxa), methods, rights and license, project and funding, and entities. Choose sections with include; long text is cut at max_text_chars and lists are capped with totals. Next: call edi_list_entities for column definitions, units and codes.

ParametersJSON Schema

Name	Required	Description
`include`	No	Sections to return: overview (abstract, keywords, dates), people, coverage (geographic, temporal, taxonomic), methods, rights, project (funding), entities. Default: all.
`package`	Yes	A package: knb-lter-hbr.14.22, knb-lter-hbr.14 (newest unless revision is set), a DOI, or a portal or PASTA URL; the scope may be a site code or name (jrn.210548103).
`revision`	No	Revision when package names none: a number, 'newest' (default) or 'oldest'.
`max_text_chars`	No	Cut abstract, methods and rights to this length.

Output Schema

ParametersJSON Schema

Name	Required	Description
`notes`	No
`title`	No
`source`	No
`license`	No
`methods`	No
`project`	No
`pubDate`	No
`abstract`	No
`contacts`	No
`coverage`	No
`creators`	No
`entities`	No
`keywords`	No
`language`	No
`resolved`	No
`nextSteps`	No
`packageId`	Yes
`publisher`	No
`shortName`	No
`emlVersion`	No
`maintenance`	No
`revisionFrom`	Yes
`creatorsTotal`	No
`entitiesTotal`	No
`keywordsTotal`	No
`abstractTruncated`	No
`associatedParties`	No
`alternateIdentifiers`	No

edi_get_packageGet an EDI data package

Read-onlyIdempotent

Overview of one package revision: title, publication date, creators, license, DOI, portal and metadata URLs, whether it is the newest revision, and its data entities with sizes and the total. Accepts package ids, series (newest unless revision is set), DOIs, portal or PASTA URLs, and site codes or scope names for the scope. Next: call edi_get_metadata for the full description or edi_list_entities for columns.

ParametersJSON Schema

Name	Required	Description	Default
`package`	Yes	A package: knb-lter-hbr.14.22, knb-lter-hbr.14 (newest unless revision is set), a DOI, or a portal or PASTA URL; the scope may be a site code or name (jrn.210548103).
`revision`	No	Revision when package names none: a number, 'newest' (default) or 'oldest'.

Output Schema

ParametersJSON Schema

Name	Required	Description
`doi`	No
`notes`	No
`title`	No
`doiUrl`	No
`series`	Yes
`source`	No
`license`	No
`pubDate`	No
`creators`	No
`entities`	Yes
`isNewest`	No
`resolved`	No
`revision`	Yes
`nextSteps`	No
`packageId`	Yes
`portalUrl`	Yes
`totalBytes`	No
`entityCount`	Yes
`metadataUrl`	Yes
`revisionFrom`	Yes
`creatorsTotal`	No
`newestRevision`	No

edi_list_entitiesList a package's data entities

Read-onlyIdempotent

Every data entity (table or file) of one package revision: name, type, file name, format, byte size, record count, CSV layout and the columns with definitions, storage types, units, date formats, code lists and missing-value codes; optional SHA-1 checksums. Gives the PASTA data URL and a DataONE URL readable without a key. Next: call edi_preview_entity or edi_download_entities with an entityId.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Entities per page (1-200).
`entity`	No	Only this entity: its id, name or file name (case-insensitive).
`offset`	No	Index of the first entity (paging).
`package`	Yes	A package: knb-lter-hbr.14.22, knb-lter-hbr.14 (newest unless revision is set), a DOI, or a portal or PASTA URL; the scope may be a site code or name (jrn.210548103).
`revision`	No	Revision when package names none: a number, 'newest' (default) or 'oldest'.
`include_checksums`	No	Fetch missing SHA-1 checksums (one request per entity, at most 25).
`include_attributes`	No	Return each entity's columns (definitions, units, codes).

Output Schema

ParametersJSON Schema

Name	Required	Description
`page`	Yes
`notes`	No
`source`	No
`entities`	Yes
`resolved`	No
`nextSteps`	No
`packageId`	Yes
`revisionFrom`	Yes
`attributesElided`	No

edi_list_identifiersList package identifiers in a scope

Read-onlyIdempotent

List the package identifiers in one scope, ascending and paginated (offset/limit). The scope may be exact (knb-lter-hbr), an LTER site code (HBR) or a name ('Hubbard Brook'). Identifiers are numbers; a package is scope.identifier.revision. Next: call edi_list_revisions(package='scope.identifier') for one identifier's revisions.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Identifiers per page (1-1000).
`scope`	Yes	A scope (knb-lter-jrn), LTER site code (JRN) or scope name or location ('Jornada', 'Hubbard Brook'); see edi_list_scopes.
`offset`	No	Index of the first identifier (paging).

Output Schema

ParametersJSON Schema

Name	Required	Description
`page`	Yes
`notes`	No
`scope`	Yes
`source`	No
`resolved`	No
`nextSteps`	No
`identifiers`	Yes

edi_list_revisionsList the revisions of a package

Read-onlyIdempotent

List every revision of one data package (scope.identifier), ascending, with the newest and oldest. Accepts a series (knb-lter-hbr.14), any revision, a DOI, a portal or PASTA URL, and site codes or scope names in place of the scope. Without an API key DataONE answers and can lag new revisions. Next: call edi_get_package(package=newestPackageId).

ParametersJSON Schema

Name	Required	Description	Default
`package`	Yes	A package series or any revision of it: knb-lter-hbr.14, knb-lter-hbr.14.22, knb-lter-hbr/14, a DOI, a portal or PASTA URL; the scope may be a site code or name (jrn.210548103).

Output Schema

ParametersJSON Schema

Name	Required	Description
`notes`	No
`scope`	Yes
`newest`	Yes
`oldest`	Yes
`series`	Yes
`source`	No
`resolved`	No
`nextSteps`	No
`revisions`	Yes
`identifier`	Yes
`newestPackageId`	Yes

edi_list_scopesList EDI scopes

Read-onlyIdempotent

List the repository's scopes (knb-lter-hbr, edi, ...) with name, kind, LTER site code, location and package counts on PASTA and DataONE. With an API key the list comes live from PASTA; without one it is edi-mcp's dated snapshot (also edi://reference/scopes). Scope arguments elsewhere also accept these site codes and names. Next: call edi_search_packages(scope=...) or edi_list_identifiers(scope=...).

ParametersJSON Schema

Name	Required	Description	Default
`kind`	No	Only one kind: lter (LTER sites), edi (general EDI submissions), bulk (generated; excluded from search by default), project, agency or other.

Output Schema

ParametersJSON Schema

Name	Required	Description
`live`	Yes
`page`	Yes
`notes`	No
`scopes`	Yes
`source`	No
`resolved`	No
`nextSteps`	No
`snapshotAsOf`	Yes

edi_pingCheck edi-mcp status

Read-onlyIdempotent

Liveness and capability report: server version and protocol, whether an EDI API key is available and therefore which backend serves this caller (pasta with a key, dataone without), which tools need a key, and whether downloads are enabled. Never reveals the key. With check_api=true it also makes one small request to that backend to confirm the key and connectivity. Next: call edi_search_packages to find data packages.

ParametersJSON Schema

Name	Required	Description	Default
`check_api`	No	Also make one small request to the backend serving this caller (with a key: exchange it for a token and list PASTA scopes; without: one DataONE query).

Output Schema

ParametersJSON Schema

Name	Required	Description
`api`	No
`pong`	No
`notes`	No
`source`	No
`backend`	Yes
`version`	Yes
`resolved`	No
`endpoints`	Yes
`keySource`	Yes
`nextSteps`	No
`transport`	Yes
`downloadDir`	No
`keyConfigured`	Yes
`protocolVersion`	Yes
`downloadsEnabled`	Yes
`keyRequiredTools`	Yes

edi_search_packagesSearch EDI data packages

Read-onlyIdempotent

Search EDI/LTER data packages by free text, scope (exact, LTER site code or name such as 'Jornada'), creator last name, temporal overlap (start_year/end_year) and bounding box; sort by relevance or publication date; paginated (offset/limit). Returns the newest revision of each package with title, DOI, coverage dates, creators and keywords. Bulk generated scopes are excluded unless include_bulk=true. Next: call edi_get_package or edi_get_metadata with a packageId.

ParametersJSON Schema

Name	Required	Description	Default
`bbox`	No	[west, south, east, north] in decimal degrees; geographic coverage must intersect it. west <= east (no antimeridian crossing).
`sort`	No	relevance, or publication date: newest or oldest (oldest lists undated packages first).	relevance
`limit`	No	Packages per page (1-50).
`query`	No	Free text over titles, keywords and abstracts (words, "phrases", AND/OR/NOT). Omit to browse with filters only.
`scope`	No	Only this scope. A scope (knb-lter-jrn), LTER site code (JRN) or scope name or location ('Jornada', 'Hubbard Brook'); see edi_list_scopes.
`author`	No	A creator's last name, e.g. 'Likens' (any case).
`offset`	No	Index of the first result (paging).
`end_year`	No	Temporal coverage starts in this year or earlier.
`start_year`	No	Temporal coverage reaches this year or later.
`include_bulk`	No	Include the generated bulk scopes (ecotrends, lter-landsat, lter-landsat-ledaps; ~36k records) when no scope is given.

Output Schema

ParametersJSON Schema

Name	Required	Description
`page`	Yes
`items`	Yes
`notes`	No
`source`	No
`resolved`	No
`nextSteps`	No
`totalExact`	Yes

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

8 tool updatesv0.1.0Oct 19, 2026
- First observededi_get_metadata
- First observededi_get_package
- First observededi_list_entities
- First observededi_list_identifiers
- First observededi_list_revisions
- First observededi_list_scopes
- First observededi_ping
- First observededi_search_packages

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

Score is being calculated.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

SYMBaiEX Evidence MCP C
com.symbaiex.www
Authenticated public evidence search, verification, research jobs, exports, and webhooks.
Search Research & Data Open Data
341
datacite-mcp-server A
io.github.cyanheads
Search DataCite datasets and software, fetch DOI metadata, trace relations, format citations.
Research & Data Open Data Search
611
NASA Earthdata MCP A
io.github.nasa
Discover, verify, and access NASA Earth science datasets via the Common Metadata Repository (CMR)
Open Data Research & Data Government Data
71
Environmental Retrieval Layer
io.github.mdlinde-sketch
Search public Australian environmental evidence with provenance across authoritative catalogues.
Open Data Government Data Search
1

Related MCP Servers

data-aggregator-mcp
Research & Data Open Data
musharna
A
license
A
quality
A
maintenance
Searches and fetches research datasets across Zenodo, DataCite (Dryad/Figshare/Dataverse/OSF), NCBI omics archives (GEO/SRA/BioProject), and the literature (PubMed/OpenAIRE) through one normalized model — deduplicating by DOI, expanding organism queries with NCBI Taxonomy synonyms, and bridging papers to the datasets they produced. Resolves citations and open-access full text, and downloads files.
Updated an hour ago (2026-10-19 21:43 UTC)
6
1,605 PyPI
4
MIT
mcp-datacite
Research & Data Open Data
pipeworx-io
A
license
Not graded
quality
B
maintenance
Provides access to DataCite DOIs for research datasets, enabling searching and retrieval of dataset metadata.
Updated 24 days ago (2026-09-25 23:24 UTC)
42 npm
MIT
io.github.krnzt/ecoscope
Research & Data Data Visualization Open Data
krnzt
A
license
Not graded
quality
B
maintenance
Enables MCP agents to discover, import, query, visualize, select, and cite NEON and local scientific datasets while keeping credentials, private paths, and bulk data out of model context.
Updated 2 months ago (2026-08-30 00:49 UTC)
MIT
neon-mcp
Open Data Research & Data
idss-mesa
A
license
A
quality
B
maintenance
Enables AI agents to discover NEON ecological data products and sites, check data availability, list and download data files, and generate citations via the NEON Data API.
Updated a month ago (2026-09-11 13:45 UTC)
20
MIT

edi-mcp

Installation

Install script

Manual

Authentication

Planned tools

License

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

data-aggregator-mcp

mcp-datacite

io.github.krnzt/ecoscope

neon-mcp