Bilinc
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BILINC_API_KEY | Yes | Bilinc Cloud API key (bil_live_...). Create one in the Bilinc Cloud dashboard at https://bilinc.space after starting the 7-day trial. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| commit_memA | Write a memory entry to hosted Bilinc Cloud. |
| recallA | Retrieve memories from hosted Bilinc Cloud. |
| reviseA | Deliberately replace an existing memory, preserving belief revision. |
| forgetA | Remove a memory from active recall. DESTRUCTIVE. |
| statusA | Report the authenticated Bilinc Cloud workspace, plan, and capabilities. Read-only and never billed. Use this to discover which lifecycle operations and recall profiles the current API key may use before attempting them. Secrets are never returned. |
| snapshotA | Create or list project checkpoints. |
| diffA | Compare a checkpoint against another checkpoint or current state. |
| rollbackA | Restore the project to a checkpoint. DESTRUCTIVE in execute mode. |
| list_memoriesA | List the memories stored in this Bilinc Cloud project. |
| historyA | Show the recorded changes to one memory key, newest first. |
| confirmA | Record that an existing memory is still accurate. |
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 11 tools
Each tool has a clearly stated role, and the descriptions actively disambiguate the risky pairs (commit_mem vs revise, forget vs revise, recall vs list_memories). A few boundaries still blur — recall vs list_memories are both reads over stored memories, and diff vs history both inspect change — but the docs give explicit guidance on when to use which.
All names are snake_case and readable, but the convention is mixed: some are bare verbs (commit_mem, recall, revise, forget, confirm), some are bare nouns (status, snapshot, history, diff), and one uses a verb_noun form (list_memories). Not chaotic, but no single predictable pattern an agent can rely on.
Eleven tools is well within the sweet spot and every one earns its place: write, read, revise, forget, confirm, inspect, checkpoint, restore, and capability discovery. No filler or near-duplicate tools.
The memory lifecycle is essentially fully covered — create, retrieve, list, revise, confirm, forget/purge, audit history, plus checkpoint/diff/rollback and status discovery. Minor gaps remain: no bulk/batch operations, no tag or source management, and no export path for migrating memories out.