Community Archive Connector
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CA_API_KEY | No | Your Community Archive API key (starts with cak_...), used to run the local stdio server. | |
| CA_ENV_FILE | No | Path to a dotenv file containing CA_API_KEY or COMMUNITY_ARCHIVE_API_KEY, which keeps the key out of client config. | |
| ALLOW_DIRECT_KEYS | No | With ALLOW_DIRECT_KEYS on (the default), /mcp also accepts Authorization: Bearer cak_... direct keys. Set to "false" to turn it off. | |
| COMMUNITY_ARCHIVE_API_KEY | No | Alternative environment variable name for your Community Archive API key, read from the env file pointed to by CA_ENV_FILE. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ca_meA | Show the calling API key's identity and rate limits. |
| ca_get_tweetsA | Fetch tweets by ID or x.com/twitter.com status URL (1–100), returned in request order. Missing IDs were deleted, opted out, or never archived. |
| ca_search_tweetsA | Full-text search across the archive: every word must appear. Filter by author, by who was replied to, and by date. Pages with offset (max 5,000). |
| ca_accountB | Profile and membership flags for one account, or for up to 100 by usernames or IDs. |
| ca_account_tweetsA | An account's tweets in time order, optionally within a date range and without replies or retweets. Cursor-paged, up to 200 per page. |
| ca_tweets_windowB | Every archived tweet created between since and until (window of at most 31 days), across all accounts. Cursor-paged. |
| ca_account_relationsB | Archive-derived likes, followers, or following for an account. Cursor-paged, up to 500 per page. |
| ca_membersB | Current Community Archive members (people who uploaded their archive). Cursor-paged, up to 1,000 per page. |
| ca_receiptA | Turn tweets into dated proof records: exact text with links expanded, timestamp, permalink, author, and a SHA-256 over kind|date|url|quote (the Receipt Cuts format), plus the API request_id as provenance. |
| ca_threadA | Reconstruct the thread around a tweet: the reply chain above it, and the author's own continuation below it. |
| ca_first_saidA | Find the earliest archived tweets containing a word or phrase, overall or by one person. Answers 'when did I first say X' and 'who said it first'. |
| ca_phrase_timelineA | Count how often a word or phrase appears per day, week, month, or year, with first and latest use and top authors. Useful for tracing how an idea spread. |
| ca_who_talks_aboutB | Find people by topic: authors who tweet about a word or phrase, ranked by how often, with their earliest mention and best-received tweet. |
| ca_find_peopleA | Find archive members by partial name or handle (fuzzy, accent-insensitive). Falls back to a direct account lookup for exact handles of non-members. |
| ca_relation_overlapB | Compare two accounts' followers or following: shared accounts and Jaccard similarity, from archive-derived edges. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Most tools occupy clearly distinct slots: fetch-by-ID (ca_get_tweets), full-text search (ca_search_tweets), per-account timeline (ca_account_tweets), and global date window (ca_tweets_window) are well separated by their descriptions. The riskiest cluster is identity lookup — ca_account vs ca_members vs ca_find_people — where an agent must pick between exact profile, member roster, and fuzzy name search, but the descriptions do state the distinctions.
Every tool shares the ca_ namespace prefix and snake_case, which keeps the set readable as a unit. Verb style is mixed, though: some are verb_noun (ca_get_tweets, ca_search_tweets, ca_find_people), others are bare nouns (ca_account, ca_members, ca_receipt, ca_thread), and a few are phrasal (ca_first_said, ca_who_talks_about, ca_me).
At 15 tools the set sits at the top of the well-scoped range, and each tool maps to a distinguishable query pattern (ID lookup, search, timeline, aggregation, relation graph) rather than duplicating another. Nothing appears redundant or padded.
The surface covers the read-only archive domain thoroughly: profiles, tweet retrieval by ID, search, per-account and global timelines, relations, threads, provenance receipts, and analytic queries (first use, phrase trends, topic experts, follow-graph overlap). Minor gaps remain — no aggregate account statistics (tweet/media counts) and no media or URL-entity listing — but these are workarounds rather than dead ends for a read-only connector.