Skip to main content
Glama

get_context

Retrieve conversation context before or after a search result to understand the full discussion. Use after searching to see surrounding messages.

Instructions

Retrieve more conversation context around a specific search result. Use ONLY after calling search, when you need to see what was discussed before or after a result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chunk_idYes
directionNo
countNo

Implementation Reference

  • The handler function that executes the get_context tool logic by fetching adjacent chunks from the database.
    export async function handleGetContext(
      db: Database.Database,
      params: GetContextParams
    ): Promise<{ content: Array<{ type: string; text: string }> }> {
      if (!params.chunk_id) {
        return {
          content: [
            { type: "text", text: JSON.stringify({ error: "chunk_id is required" }) },
          ],
        };
      }
    
      const direction = params.direction || "both";
      const count = Math.min(params.count || 3, 10);
    
      // Look up the anchor chunk
      const anchor = db
        .prepare(
          "SELECT id, session_id, chunk_index, role, content, timestamp, turn_start, turn_end, token_count FROM chunks WHERE id = ?"
        )
        .get(params.chunk_id) as ChunkRow | undefined;
    
      if (!anchor) {
        return {
          content: [
            { type: "text", text: JSON.stringify({ error: "Chunk not found" }) },
          ],
        };
      }
    
      // Fetch adjacent chunks according to direction
      const beforeCount = direction === "after" ? 0 : count;
      const afterCount = direction === "before" ? 0 : count;
    
      const { before, after } = getAdjacentChunks(db, {
        session_id: anchor.session_id,
        chunk_index: anchor.chunk_index,
        before: beforeCount,
        after: afterCount,
      });
    
      // Get session info for the anchor chunk
      const session = db
        .prepare(
          `SELECT s.session_id, p.path as project
           FROM sessions s JOIN projects p ON p.id = s.project_id
           WHERE s.id = ?`
        )
        .get(anchor.session_id) as { session_id: string; project: string } | undefined;
    
      const result = {
        anchor: {
          chunk_id: anchor.id,
          content: anchor.content,
          timestamp: anchor.timestamp,
          role: anchor.role,
        },
        before: before.map((c) => ({
          chunk_id: c.id,
          content: c.content,
          timestamp: c.timestamp,
          role: c.role,
        })),
        after: after.map((c) => ({
          chunk_id: c.id,
          content: c.content,
          timestamp: c.timestamp,
          role: c.role,
        })),
        session_id: session?.session_id || "",
        project: session?.project || "",
      };
    
      return { content: [{ type: "text", text: JSON.stringify(result) }] };
    }
  • Type definition for the parameters of the get_context tool.
    export interface GetContextParams {
      chunk_id: number;
      direction?: "before" | "after" | "both";
      count?: number;
    }
  • src/server.ts:48-60 (registration)
    Registration of the get_context tool in the MCP server.
    // get_context tool
    server.tool(
      "get_context",
      "Retrieve more conversation context around a specific search result. Use ONLY after calling search, when you need to see what was discussed before or after a result.",
      {
        chunk_id: z.number(),
        direction: z.enum(["before", "after", "both"]).optional(),
        count: z.number().optional(),
      },
      async (args): Promise<ToolResult> => {
        return handleGetContext(db, {
          chunk_id: args.chunk_id,
          direction: args.direction,

Tool Definition Quality

Score is being calculated. Check back soon.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hyunjae-labs/lore'

If you have feedback or need assistance with the MCP directory API, please join our Discord server