pathmark
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PATHMARK_STORE_DIR | No | Directory for memory.jsonl. Default: ~/.pathmark/memory | |
| PATHMARK_CODEX_MODEL | No | Optional Codex model override. Default: unset | |
| PATHMARK_CHAT_COMMAND | No | Command provider: receives a synthesized prompt on stdin and writes an answer on stdout. Default: unset | |
| PATHMARK_OPENAI_MODEL | No | Model id for OpenAI-compatible synthesis. Default: unset | |
| PATHMARK_CODEX_COMMAND | No | Codex provider command. Default: codex | |
| PATHMARK_OPENAI_API_KEY | No | OpenAI-compatible API key. Default: unset | |
| PATHMARK_CHAT_TIMEOUT_MS | No | Synthesis command timeout. Default: 120000 | |
| PATHMARK_OPENAI_BASE_URL | No | OpenAI-compatible API base URL. Default: https://api.openai.com/v1 | |
| PATHMARK_MAX_SEARCH_RESULTS | No | Default search limit. Default: 12 | |
| PATHMARK_SYNTHESIS_PROVIDER | No | Synthesis provider: client, command, codex, or openai-compatible. Default: client |
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 |
|---|---|
| get_configA | Show the local Pathmark Memory store location and enabled optional features. |
| rememberA | Save raw searchable evidence. Durable intent should use the approval-gated conclusion workflow. |
| create_conclusionC | Propose a durable higher-signal conclusion. Approval is required by default before it can be recalled. |
| search_memoryB | Search saved local memories and conclusions. |
| get_contextC | Return compact local memory context for a task or question. |
| recall_memoryB | Transparent recall for any MCP-capable harness. Use this at task start or before answering to show exactly which memories were used. |
| session_traceA | Show a bounded chronological audit trail for one captured session: prompts, exact injected memory IDs, redacted tool inputs/results, and answers. |
| rate_recallC | Attach explicit relevance labels to one exact Pathmark recall so audit_memory can report measured precision. |
| list_conclusionsC | List saved durable conclusions. |
| list_pending_conclusionsA | List bounded approval-gated conclusion proposals. Pending records are never returned by normal memory search. |
| approve_conclusionA | Approve one pending conclusion, optionally correcting its text or tags. The transition is atomic and auditable. |
| reject_conclusionA | Reject one pending conclusion while retaining it in the canonical audit trail and excluding it from recall. |
| get_memory_snapshotB | Generate a bounded USER/PROJECT/AGENT snapshot from approved canonical conclusions only. |
| delete_memoryA | Soft-delete a saved memory or conclusion by id. |
| update_memoryC | Correct an existing memory while preserving its prior versions in local history. |
| supersede_memoryC | Replace an outdated memory with a linked current record while preserving history. |
| purge_memoryC | Preview or permanently remove matching records from the canonical store. A backup is created before an applied purge. |
| consolidate_memoryB | Prepare a bounded unsynthesized evidence batch and, when server synthesis is configured, preview or stage evidence-backed conclusion proposals. Proposals are never auto-approved. |
| audit_memoryA | Measure capture-to-recall behavior, unused records, recall age, duplicate rate, stale raw hits, and available precision evidence without changing memory. |
| doctor_memoryA | Report duplicate, deleted, expired, conclusion, invalid-record, and index health counts without changing data. |
| compact_memoryA | Preview or apply exact deduplication, expired-record removal, retention, and deleted-record purging. Applied runs create a backup. |
| backup_memoryC | Create a point-in-time copy of the canonical local JSONL store. |
| export_memoryB | Export a scoped, mergeable JSONL bundle for another Pathmark installation or trusted sync transport. |
| ask_memoryA | Ask approved conclusions first, then scoped or explicitly requested raw evidence. Returns an answer, exact provenance, and a recallId for feedback. |
| chatB | Chat with Pathmark using approved conclusions first and only scoped or explicitly requested raw fallback. Returns an answer, provenance, and recallId. |
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 25 tools
chat and ask_memory are nearly identical in purpose—both answer using approved conclusions first with raw fallback and return provenance plus a recallId—creating clear ambiguity. Additionally, search_memory, get_context, recall_memory, and ask_memory overlap in retrieval behavior, though their descriptions partially clarify output differences. The raw-evidence tools (remember, create_conclusion, consolidate_memory) are more distinct but still require careful reading.
Most tools follow a consistent verb_noun snake_case pattern such as create_conclusion, approve_conclusion, delete_memory, and export_memory. A few bare-verb or noun-like names like remember, chat, and session_trace deviate slightly, but the overall convention is recognizable and predictable.
At 25 tools, this sits at the heavy end of the borderline range and feels like more surface than most agents will need. The count is defensible for a full memory lifecycle system covering capture, recall, conclusions, audit, and maintenance, but it risks overwhelming users.
The tool set covers the core memory lifecycle well: capture raw evidence, propose and approve conclusions, search and recall, update/delete/supersede, audit, compact, backup, and export. Minor gaps exist—there is no import tool to complement export, and no direct get-by-id retrieval—but agents can work around these via search and export/backup workflows.