airkjw/claude-mem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Refactor mem-search operations: remove outdated documentation files, enhance search parameters, and improve token efficiency guidelines. Update MCP server descriptions for clarity on search and timeline functionalities. Remove unnecessary zip build process for mem-search skill.

Browse Source
This commit is contained in:
Alex Newman
2025-12-28 23:32:52 -05:00
parent 979918d202
commit 0e913a25ff
21 changed files with 4 additions and 2744 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/servers/mcp-server.ts
+3 -3
View File
@@ -185,7 +185,7 @@ NEVER fetch full details without filtering first. 10x token savings.`,
},
{
name: 'search',
description: 'Step 1: Search memory. Returns index with IDs. Params: query, limit, project, type, obs_type, dateStart, dateEnd',
description: 'Step 1: Search memory. Returns index with IDs. Params: query, limit, project, type, obs_type, dateStart, dateEnd, offset, orderBy',
inputSchema: {
type: 'object',
properties: {},
@@ -198,7 +198,7 @@ NEVER fetch full details without filtering first. 10x token savings.`,
},
{
name: 'timeline',
description: 'Step 2: Get context around results. Params: anchor (observation ID), depth_before, depth_after, project',
description: 'Step 2: Get context around results. Params: anchor (observation ID) OR query (finds anchor automatically), depth_before, depth_after, project',
inputSchema: {
type: 'object',
properties: {},
@@ -211,7 +211,7 @@ NEVER fetch full details without filtering first. 10x token savings.`,
},
{
name: 'get_observations',
description: 'Step 3: Fetch full details for filtered IDs. Params: ids (array of observation IDs), project',
description: 'Step 3: Fetch full details for filtered IDs. Params: ids (array of observation IDs, required), orderBy, limit, project',
inputSchema: {
type: 'object',
properties: {